Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5892 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.5595. Min Act: -0.1700
Data Index: 6297013 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.4970. Min Act: -0.1700
Data Index: 8289733 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.3720. Min Act: -0.1700
Data Index: 1156641 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.3720. Min Act: -0.1700
Data Index: 5876055 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.3720. Min Act: -0.1700
Data Index: 3323676 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.1845. Min Act: -0.1700
Data Index: 1230500 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.1220. Min Act: -0.1699
Data Index: 5070930 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.1220. Min Act: -0.1700
Data Index: 2706746 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.1220. Min Act: -0.1700
Data Index: 4680677 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5595. Min Range: -11.5595
Max Act: 11.0595. Min Act: -0.1700
Data Index: 5599518 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.9970. Min Act: -0.1700
Data Index: 4354247 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.9970. Min Act: -0.1700
Data Index: 7658939 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.9970. Min Act: -0.1700
Data Index: 5381575 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.8720. Min Act: -0.1700
Data Index: 5768282 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.8720. Min Act: -0.1700
Data Index: 4611373 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.8720. Min Act: -0.1700
Data Index: 2332709 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.8720. Min Act: -0.1700
Data Index: 5033841 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.8720. Min Act: -0.1700
Data Index: 6115355 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.8720. Min Act: -0.1700
Data Index: 2219849 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5595. Min Range: -11.5595
Max Act: 10.8720. Min Act: -0.1700
Data Index: 327010 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19