Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2330 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.4489. Min Act: -0.1700
Data Index: 5004638 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.3239. Min Act: -0.1700
Data Index: 7945055 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.3551. Min Act: -0.1700
Data Index: 1885421 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.3239. Min Act: -0.1700
Data Index: 1001606 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.2926. Min Act: -0.1700
Data Index: 8773774 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.2926. Min Act: -0.1700
Data Index: 825144 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.2614. Min Act: -0.1700
Data Index: 95501 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.1989. Min Act: -0.1700
Data Index: 8534102 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.1989. Min Act: -0.1700
Data Index: 6451378 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.1676. Min Act: -0.1700
Data Index: 7507706 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.1364. Min Act: -0.1700
Data Index: 6451383 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.0426. Min Act: -0.1700
Data Index: 7915979 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.0426. Min Act: -0.1700
Data Index: 8451366 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.0114. Min Act: -0.1700
Data Index: 561038 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.0114. Min Act: -0.1700
Data Index: 2830962 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4489. Min Range: -7.4489
Max Act: 7.0114. Min Act: -0.1700
Data Index: 1436227 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4489. Min Range: -7.4489
Max Act: 6.9801. Min Act: -0.1700
Data Index: 8245899 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4489. Min Range: -7.4489
Max Act: 6.9489. Min Act: -0.1700
Data Index: 6598882 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4489. Min Range: -7.4489
Max Act: 6.9801. Min Act: -0.1700
Data Index: 6133331 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4489. Min Range: -7.4489
Max Act: 6.9489. Min Act: -0.1700
Data Index: 1129955 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19