Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6052 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.9932. Min Act: -0.1700
Data Index: 907091 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.4932. Min Act: -0.1700
Data Index: 357518 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.4932. Min Act: -0.1700
Data Index: 5678069 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.3682. Min Act: -0.1700
Data Index: 1213767 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.2432. Min Act: -0.1700
Data Index: 4725238 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.2432. Min Act: -0.1700
Data Index: 5837704 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.3057. Min Act: -0.1700
Data Index: 118476 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.2432. Min Act: -0.1700
Data Index: 280135 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.2432. Min Act: -0.1700
Data Index: 5189451 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.2432. Min Act: -0.1700
Data Index: 7226777 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.2432. Min Act: -0.1700
Data Index: 2993241 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.3057. Min Act: -0.1700
Data Index: 6338683 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1807. Min Act: -0.1700
Data Index: 2788915 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1807. Min Act: -0.1700
Data Index: 6990686 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1807. Min Act: -0.1700
Data Index: 365251 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1182. Min Act: -0.1700
Data Index: 1819953 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1807. Min Act: -0.1700
Data Index: 525031 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1807. Min Act: -0.1700
Data Index: 5395143 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1182. Min Act: -0.1700
Data Index: 3539985 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9932. Min Range: -9.9932
Max Act: 9.1807. Min Act: -0.1700
Data Index: 2795544 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19