Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 332 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.5501. Min Act: -0.1700
Data Index: 434383 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.4251. Min Act: -0.1700
Data Index: 3776557 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.3314. Min Act: -0.1700
Data Index: 1371948 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.3314. Min Act: -0.1700
Data Index: 7901016 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.3001. Min Act: -0.1700
Data Index: 1715501 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2689. Min Act: -0.1700
Data Index: 7143054 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2689. Min Act: -0.1700
Data Index: 217439 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2376. Min Act: -0.1700
Data Index: 7822126 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2376. Min Act: -0.1700
Data Index: 4800959 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2064. Min Act: -0.1700
Data Index: 5955675 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2064. Min Act: -0.1700
Data Index: 7330497 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2064. Min Act: -0.1700
Data Index: 1289860 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.2064. Min Act: -0.1700
Data Index: 3014426 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.1751. Min Act: -0.1700
Data Index: 3536420 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.1751. Min Act: -0.1700
Data Index: 883942 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.1439. Min Act: -0.1700
Data Index: 5336080 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.1126. Min Act: -0.1700
Data Index: 2703840 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.1126. Min Act: -0.1700
Data Index: 7750919 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.1126. Min Act: -0.1700
Data Index: 55833 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5501. Min Range: -4.5501
Max Act: 4.0813. Min Act: -0.1700
Data Index: 2872593 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19