Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4321 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.3352. Min Act: -0.1700
Data Index: 4323363 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.3352. Min Act: -0.1700
Data Index: 6024419 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.3040. Min Act: -0.1700
Data Index: 2755132 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.2415. Min Act: -0.1700
Data Index: 8513755 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.2415. Min Act: -0.1700
Data Index: 7368451 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.2415. Min Act: -0.1700
Data Index: 8493952 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.2102. Min Act: -0.1700
Data Index: 3459206 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.2102. Min Act: -0.1700
Data Index: 6940479 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.2102. Min Act: -0.1700
Data Index: 7720675 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.1477. Min Act: -0.1700
Data Index: 1279981 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.1477. Min Act: -0.1700
Data Index: 5793731 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.1477. Min Act: -0.1700
Data Index: 5353407 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.1164. Min Act: -0.1700
Data Index: 2241978 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.1164. Min Act: -0.1700
Data Index: 1587450 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.1164. Min Act: -0.1700
Data Index: 3493774 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.1164. Min Act: -0.1700
Data Index: 6135313 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.0852. Min Act: -0.1700
Data Index: 3251933 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.0852. Min Act: -0.1700
Data Index: 4646010 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.0539. Min Act: -0.1700
Data Index: 3248558 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3352. Min Range: -4.3352
Max Act: 4.0539. Min Act: -0.1700
Data Index: 7903548 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19