Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4331 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3695. Min Range: -8.3695
Max Act: 8.3695. Min Act: -0.1700
Data Index: 856540 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3695. Min Range: -8.3695
Max Act: 8.1820. Min Act: -0.1700
Data Index: 2482352 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3695. Min Range: -8.3695
Max Act: 8.2445. Min Act: -0.1700
Data Index: 2149241 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.9945. Min Act: -0.1700
Data Index: 4702554 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.9320. Min Act: -0.1700
Data Index: 3864775 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.9320. Min Act: -0.1700
Data Index: 4642875 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.9320. Min Act: -0.1700
Data Index: 5785291 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8695. Min Act: -0.1700
Data Index: 4197222 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8695. Min Act: -0.1700
Data Index: 4346824 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8695. Min Act: -0.1700
Data Index: 4888295 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8695. Min Act: -0.1700
Data Index: 8199330 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8695. Min Act: -0.1700
Data Index: 1756281 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8695. Min Act: -0.1700
Data Index: 1061239 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8070. Min Act: -0.1700
Data Index: 6649977 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8070. Min Act: -0.1700
Data Index: 7613732 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.8070. Min Act: -0.1700
Data Index: 6793754 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.7445. Min Act: -0.1700
Data Index: 2486905 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.7445. Min Act: -0.1700
Data Index: 2148932 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.7445. Min Act: -0.1700
Data Index: 5841584 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3695. Min Range: -8.3695
Max Act: 7.7445. Min Act: -0.1700
Data Index: 1462001 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19