Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4614 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.8445. Min Act: -0.1700
Data Index: 8019276 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.8445. Min Act: -0.1700
Data Index: 8035912 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.8132. Min Act: -0.1700
Data Index: 5585197 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.7820. Min Act: -0.1700
Data Index: 2119492 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.7820. Min Act: -0.1700
Data Index: 234858 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.7195. Min Act: -0.1700
Data Index: 3264844 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6882. Min Act: -0.1697
Data Index: 2428414 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6882. Min Act: -0.1700
Data Index: 676625 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6570. Min Act: -0.1700
Data Index: 2654133 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6570. Min Act: -0.1700
Data Index: 7766703 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6882. Min Act: -0.1700
Data Index: 6458832 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6570. Min Act: -0.1700
Data Index: 2265175 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6882. Min Act: -0.1699
Data Index: 1921360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6257. Min Act: -0.1700
Data Index: 5691235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.5945. Min Act: -0.1700
Data Index: 6872411 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6257. Min Act: -0.1700
Data Index: 3797182 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.6257. Min Act: -0.1700
Data Index: 6200439 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.5945. Min Act: -0.1700
Data Index: 1128018 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.5945. Min Act: -0.1700
Data Index: 5275697 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8445. Min Range: -5.8445
Max Act: 5.5945. Min Act: -0.1700
Data Index: 3739873 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19