Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.4658. Min Act: -0.1700
Data Index: 6126828 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.3720. Min Act: -0.1700
Data Index: 5954307 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.3408. Min Act: -0.1700
Data Index: 134934 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2783. Min Act: -0.1700
Data Index: 5889290 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2470. Min Act: -0.1700
Data Index: 5522032 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2158. Min Act: -0.1700
Data Index: 2085707 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2470. Min Act: -0.1700
Data Index: 1586710 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2470. Min Act: -0.1700
Data Index: 3091295 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2158. Min Act: -0.1700
Data Index: 7628021 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1845. Min Act: -0.1700
Data Index: 6649885 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1533. Min Act: -0.1700
Data Index: 6660763 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3152177 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3584674 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3399756 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3327203 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1220. Min Act: -0.1700
Data Index: 4117970 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1533. Min Act: -0.1700
Data Index: 8436205 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1533. Min Act: -0.1700
Data Index: 8301477 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1845. Min Act: -0.1700
Data Index: 767146 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.1220. Min Act: -0.1700
Data Index: 2908129 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19