Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5688 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5967. Min Range: -10.5967
Max Act: 10.5967. Min Act: -0.1700
Data Index: 656989 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5967. Min Range: -10.5967
Max Act: 10.1592. Min Act: -0.1700
Data Index: 6583227 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5967. Min Range: -10.5967
Max Act: 10.0967. Min Act: -0.1700
Data Index: 2889691 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.6592. Min Act: -0.1700
Data Index: 87930 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.6592. Min Act: -0.1700
Data Index: 8509777 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.5967. Min Act: -0.1700
Data Index: 6253503 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.5342. Min Act: -0.1700
Data Index: 6900357 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.5342. Min Act: -0.1700
Data Index: 4430417 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.4092. Min Act: -0.1700
Data Index: 8106819 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.4092. Min Act: -0.1700
Data Index: 1529025 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.4092. Min Act: -0.1700
Data Index: 2354252 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.4092. Min Act: -0.1700
Data Index: 7463498 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.4092. Min Act: -0.1700
Data Index: 4095252 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.4092. Min Act: -0.1700
Data Index: 981772 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.3467. Min Act: -0.1700
Data Index: 6401634 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.2842. Min Act: -0.1700
Data Index: 1021351 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.3467. Min Act: -0.1700
Data Index: 254366 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.3467. Min Act: -0.1700
Data Index: 729030 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.2842. Min Act: -0.1700
Data Index: 5427898 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5967. Min Range: -10.5967
Max Act: 9.2842. Min Act: -0.1700
Data Index: 5628610 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19