Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 697 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.4143. Min Act: -0.1700
Data Index: 2554515 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.4143. Min Act: -0.1700
Data Index: 1313168 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3830. Min Act: -0.1700
Data Index: 3512321 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3518. Min Act: -0.1700
Data Index: 7644441 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3518. Min Act: -0.1700
Data Index: 7532294 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3518. Min Act: -0.1700
Data Index: 6867747 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3518. Min Act: -0.1700
Data Index: 5612179 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3518. Min Act: -0.1700
Data Index: 1197717 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3205. Min Act: -0.1700
Data Index: 5693434 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3205. Min Act: -0.1700
Data Index: 1609678 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3205. Min Act: -0.1700
Data Index: 3294231 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.3205. Min Act: -0.1700
Data Index: 412785 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2893. Min Act: -0.1700
Data Index: 7896724 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2893. Min Act: -0.1700
Data Index: 8667098 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2893. Min Act: -0.1700
Data Index: 4486457 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2580. Min Act: -0.1700
Data Index: 4209066 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2268. Min Act: -0.1698
Data Index: 4450997 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2580. Min Act: -0.1700
Data Index: 5973076 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2580. Min Act: -0.1700
Data Index: 6017117 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2580. Min Act: -0.1700
Data Index: 6192583 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19