Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 883 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1033. Min Range: -10.1033
Max Act: 10.1033. Min Act: -0.1700
Data Index: 8769974 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1033. Min Range: -10.1033
Max Act: 10.0408. Min Act: -0.1700
Data Index: 2312903 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.9783. Min Act: -0.1700
Data Index: 4381867 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.9158. Min Act: -0.1700
Data Index: 8212389 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.8533. Min Act: -0.1700
Data Index: 5373828 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.8533. Min Act: -0.1700
Data Index: 4381865 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.8533. Min Act: -0.1700
Data Index: 7410373 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.7908. Min Act: -0.1700
Data Index: 116040 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.7283. Min Act: -0.1700
Data Index: 7128000 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.7283. Min Act: -0.1700
Data Index: 3210508 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6658. Min Act: -0.1700
Data Index: 948492 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6658. Min Act: -0.1700
Data Index: 5336027 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6658. Min Act: -0.1700
Data Index: 7301540 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6658. Min Act: -0.1700
Data Index: 2044405 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6658. Min Act: -0.1700
Data Index: 7816148 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6658. Min Act: -0.1700
Data Index: 6986824 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6033. Min Act: -0.1700
Data Index: 8061265 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6033. Min Act: -0.1700
Data Index: 4118154 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.6033. Min Act: -0.1700
Data Index: 5203136 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1033. Min Range: -10.1033
Max Act: 9.5408. Min Act: -0.1700
Data Index: 905541 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19