Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 436 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1347. Min Range: -10.1347
Max Act: 10.1347. Min Act: -0.1700
Data Index: 3080079 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1347. Min Range: -10.1347
Max Act: 10.0722. Min Act: -0.1700
Data Index: 4721153 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1347. Min Range: -10.1347
Max Act: 9.6347. Min Act: -0.1700
Data Index: 6434224 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1347. Min Range: -10.1347
Max Act: 9.1972. Min Act: -0.1700
Data Index: 5286547 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1347. Min Range: -10.1347
Max Act: 9.0097. Min Act: -0.1700
Data Index: 8087323 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1347. Min Range: -10.1347
Max Act: 9.0097. Min Act: -0.1700
Data Index: 6300944 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1347. Min Range: -10.1347
Max Act: 9.0097. Min Act: -0.1700
Data Index: 1846785 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.9472. Min Act: -0.1700
Data Index: 4826779 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.9472. Min Act: -0.1700
Data Index: 7236696 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.8847. Min Act: -0.1700
Data Index: 3148228 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.7597. Min Act: -0.1700
Data Index: 1001654 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.7597. Min Act: -0.1700
Data Index: 5870756 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.7597. Min Act: -0.1700
Data Index: 5186986 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.7597. Min Act: -0.1700
Data Index: 8603438 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.6972. Min Act: -0.1700
Data Index: 4125846 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.6347. Min Act: -0.1700
Data Index: 1811151 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.6347. Min Act: -0.1700
Data Index: 3781173 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.5722. Min Act: -0.1700
Data Index: 1331377 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.5722. Min Act: -0.1700
Data Index: 4780184 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1347. Min Range: -10.1347
Max Act: 8.5722. Min Act: -0.1700
Data Index: 2438717 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19