Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.6091. Min Act: -0.1700
Data Index: 8239464 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.4528. Min Act: -0.1700
Data Index: 8827075 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.3903. Min Act: -0.1700
Data Index: 901849 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.3903. Min Act: -0.1700
Data Index: 4870697 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.3591. Min Act: -0.1700
Data Index: 2514923 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2966. Min Act: -0.1700
Data Index: 4215321 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2653. Min Act: -0.1700
Data Index: 7135658 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2341. Min Act: -0.1700
Data Index: 6217073 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2341. Min Act: -0.1700
Data Index: 2077011 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 5584336 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2341. Min Act: -0.1700
Data Index: 2834782 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2341. Min Act: -0.1700
Data Index: 6921456 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 2313372 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 6639672 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 4500305 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 5882437 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 2829032 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 6100852 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.2028. Min Act: -0.1700
Data Index: 4762709 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6091. Min Range: -5.6091
Max Act: 5.1403. Min Act: -0.1700
Data Index: 6310062 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19