Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 137 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.4293. Min Act: -0.1700
Data Index: 8033808 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.2418. Min Act: -0.1700
Data Index: 6669092 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 4027375 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1168. Min Act: -0.1700
Data Index: 225887 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.0543. Min Act: -0.1700
Data Index: 8079104 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.9293. Min Act: -0.1700
Data Index: 5694317 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.8668. Min Act: -0.1700
Data Index: 3990866 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.7418. Min Act: -0.1700
Data Index: 489574 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.7418. Min Act: -0.1700
Data Index: 7986366 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.5855. Min Act: -0.1700
Data Index: 6327030 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.5855. Min Act: -0.1700
Data Index: 2616845 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.5543. Min Act: -0.1700
Data Index: 1040354 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.5855. Min Act: -0.1700
Data Index: 4013747 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.5230. Min Act: -0.1700
Data Index: 5743093 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.5543. Min Act: -0.1700
Data Index: 5388257 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.5230. Min Act: -0.1700
Data Index: 7961611 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.4918. Min Act: -0.1700
Data Index: 5415776 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.3980. Min Act: -0.1700
Data Index: 2642782 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.3980. Min Act: -0.1700
Data Index: 1185277 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4293. Min Range: -8.4293
Max Act: 7.3980. Min Act: -0.1700
Data Index: 6715550 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19