Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3324 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.4167. Min Act: -0.1700
Data Index: 4268400 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3677. Min Act: -0.1698
Data Index: 521041 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3677. Min Act: -0.1699
Data Index: 2764580 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3513. Min Act: -0.1697
Data Index: 8295654 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3513. Min Act: -0.1700
Data Index: 2282248 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3185. Min Act: -0.1700
Data Index: 3675053 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3349. Min Act: -0.1700
Data Index: 2822835 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3185. Min Act: -0.1700
Data Index: 41261 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3021. Min Act: -0.1700
Data Index: 5195281 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3185. Min Act: -0.1700
Data Index: 3765252 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3185. Min Act: -0.1700
Data Index: 397868 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3185. Min Act: -0.1700
Data Index: 42771 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3021. Min Act: -0.1700
Data Index: 4254607 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3021. Min Act: -0.1700
Data Index: 2858418 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3021. Min Act: -0.1700
Data Index: 2666025 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.3021. Min Act: -0.1700
Data Index: 2489400 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.2856. Min Act: -0.1700
Data Index: 2785707 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.2856. Min Act: -0.1700
Data Index: 699466 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.2856. Min Act: -0.1699
Data Index: 4591536 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4167. Min Range: -2.4167
Max Act: 2.2691. Min Act: -0.1700
Data Index: 5748517 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19