Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0342. Min Range: -3.0342
Max Act: 3.0342. Min Act: -0.1700
Data Index: 5315414 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0342. Min Range: -3.0342
Max Act: 3.0342. Min Act: -0.1700
Data Index: 3260923 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.9552. Min Act: -0.1683
Data Index: 6456010 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.9393. Min Act: -0.1683
Data Index: 1279415 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.8918. Min Act: -0.1700
Data Index: 1570281 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.8918. Min Act: -0.1695
Data Index: 4159009 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.8442. Min Act: -0.1683
Data Index: 4159032 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.8442. Min Act: -0.1700
Data Index: 1279444 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7964. Min Act: -0.1700
Data Index: 3167352 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.8124. Min Act: -0.1700
Data Index: 1007148 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.8124. Min Act: -0.1700
Data Index: 5716682 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7964. Min Act: -0.1700
Data Index: 5629877 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7964. Min Act: -0.1700
Data Index: 3260908 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7964. Min Act: -0.1696
Data Index: 2657193 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7964. Min Act: -0.1700
Data Index: 5831589 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7805. Min Act: -0.1700
Data Index: 7633227 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7805. Min Act: -0.1700
Data Index: 5709358 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7805. Min Act: -0.1700
Data Index: 4159010 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7805. Min Act: -0.1700
Data Index: 6225803 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0342. Min Range: -3.0342
Max Act: 2.7646. Min Act: -0.1697
Data Index: 5709360 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19