Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6013 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.4288. Min Act: -0.1700
Data Index: 4238744 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.3190. Min Act: -0.1700
Data Index: 1975324 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.2562. Min Act: -0.1700
Data Index: 784728 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.2091. Min Act: -0.1700
Data Index: 7492957 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1933. Min Act: -0.1700
Data Index: 6839488 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.2091. Min Act: -0.1700
Data Index: 8692229 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1776. Min Act: -0.1700
Data Index: 2854293 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1776. Min Act: -0.1700
Data Index: 7747810 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1933. Min Act: -0.1700
Data Index: 8413606 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1933. Min Act: -0.1700
Data Index: 7620882 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1776. Min Act: -0.1700
Data Index: 1954294 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1776. Min Act: -0.1700
Data Index: 7716814 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1776. Min Act: -0.1700
Data Index: 5790457 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1933. Min Act: -0.1700
Data Index: 1059773 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1619. Min Act: -0.1700
Data Index: 4140060 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1619. Min Act: -0.1700
Data Index: 4161013 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1461. Min Act: -0.1700
Data Index: 1973398 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1461. Min Act: -0.1700
Data Index: 7242579 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1304. Min Act: -0.1700
Data Index: 2372112 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4288. Min Range: -3.4288
Max Act: 3.1304. Min Act: -0.1700
Data Index: 6861652 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19