Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.9138. Min Act: -0.1700
Data Index: 3517286 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.6326. Min Act: -0.1700
Data Index: 6544910 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.6326. Min Act: -0.1700
Data Index: 4604834 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.6326. Min Act: -0.1700
Data Index: 4155583 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.6013. Min Act: -0.1700
Data Index: 1292015 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.5388. Min Act: -0.1700
Data Index: 4538556 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.5388. Min Act: -0.1700
Data Index: 3540874 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.5388. Min Act: -0.1700
Data Index: 5065938 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.5076. Min Act: -0.1700
Data Index: 1991453 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.5076. Min Act: -0.1700
Data Index: 2341502 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.4451. Min Act: -0.1700
Data Index: 3035948 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.4138. Min Act: -0.1700
Data Index: 763720 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.4138. Min Act: -0.1700
Data Index: 744423 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3826. Min Act: -0.1700
Data Index: 3398953 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.4138. Min Act: -0.1700
Data Index: 2076177 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3513. Min Act: -0.1700
Data Index: 5350973 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3201. Min Act: -0.1700
Data Index: 5560722 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3201. Min Act: -0.1700
Data Index: 5942467 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3201. Min Act: -0.1700
Data Index: 1520013 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3201. Min Act: -0.1700
Data Index: 3524272 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19