Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0386. Min Range: -4.0386
Max Act: 4.0386. Min Act: -0.1700
Data Index: 2862482 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.9135. Min Act: -0.1700
Data Index: 6266893 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.7885. Min Act: -0.1700
Data Index: 5564533 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.7415. Min Act: -0.1700
Data Index: 6942274 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6790. Min Act: -0.1700
Data Index: 5118823 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6946. Min Act: -0.1700
Data Index: 7038701 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6790. Min Act: -0.1700
Data Index: 606998 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6477. Min Act: -0.1700
Data Index: 1033981 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6477. Min Act: -0.1700
Data Index: 6794968 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6007. Min Act: -0.1700
Data Index: 1719673 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6007. Min Act: -0.1700
Data Index: 7036072 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6164. Min Act: -0.1700
Data Index: 5825109 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6007. Min Act: -0.1700
Data Index: 2983922 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6007. Min Act: -0.1700
Data Index: 8212194 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.5694. Min Act: -0.1700
Data Index: 4006438 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.5851. Min Act: -0.1700
Data Index: 3666142 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.5694. Min Act: -0.1700
Data Index: 7523517 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.5851. Min Act: -0.1700
Data Index: 6754552 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.5851. Min Act: -0.1700
Data Index: 5556840 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0386. Min Range: -4.0386
Max Act: 3.6007. Min Act: -0.1700
Data Index: 6956865 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19