Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4345 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1135. Min Range: -7.1135
Max Act: 7.1135. Min Act: -0.1700
Data Index: 176547 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1135. Min Range: -7.1135
Max Act: 7.0510. Min Act: -0.1700
Data Index: 5399951 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1135. Min Range: -7.1135
Max Act: 7.0198. Min Act: -0.1700
Data Index: 6243244 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.8010. Min Act: -0.1700
Data Index: 3583612 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.8010. Min Act: -0.1700
Data Index: 4074664 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.7385. Min Act: -0.1700
Data Index: 7081895 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.7385. Min Act: -0.1700
Data Index: 1881527 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.7385. Min Act: -0.1700
Data Index: 4074666 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.6760. Min Act: -0.1700
Data Index: 1477937 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.6760. Min Act: -0.1700
Data Index: 956635 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.5823. Min Act: -0.1700
Data Index: 1859455 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.5510. Min Act: -0.1700
Data Index: 3475559 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.5510. Min Act: -0.1700
Data Index: 2374167 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.5198. Min Act: -0.1700
Data Index: 5087489 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.4885. Min Act: -0.1700
Data Index: 1488080 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.5198. Min Act: -0.1700
Data Index: 2997079 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.5198. Min Act: -0.1700
Data Index: 1488079 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.5198. Min Act: -0.1700
Data Index: 7039619 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.4885. Min Act: -0.1700
Data Index: 4614295 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1135. Min Range: -7.1135
Max Act: 6.4885. Min Act: -0.1700
Data Index: 956631 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19