Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1617. Min Range: -4.1617
Max Act: 4.1617. Min Act: -0.1700
Data Index: 2727007 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1617. Min Range: -4.1617
Max Act: 4.0054. Min Act: -0.1700
Data Index: 1685862 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.9741. Min Act: -0.1700
Data Index: 7934049 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.9741. Min Act: -0.1700
Data Index: 1769394 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8959. Min Act: -0.1700
Data Index: 1263885 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8803. Min Act: -0.1700
Data Index: 6160424 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8959. Min Act: -0.1700
Data Index: 686074 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8647. Min Act: -0.1700
Data Index: 2544656 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8803. Min Act: -0.1700
Data Index: 3285962 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8334. Min Act: -0.1700
Data Index: 6760778 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8647. Min Act: -0.1700
Data Index: 5580875 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8490. Min Act: -0.1700
Data Index: 1246916 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8647. Min Act: -0.1700
Data Index: 6074349 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8490. Min Act: -0.1700
Data Index: 3995221 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8334. Min Act: -0.1700
Data Index: 5383573 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8178. Min Act: -0.1700
Data Index: 1227182 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.8178. Min Act: -0.1700
Data Index: 3123346 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.7865. Min Act: -0.1700
Data Index: 3358999 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.7865. Min Act: -0.1700
Data Index: 7306660 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1617. Min Range: -4.1617
Max Act: 3.7865. Min Act: -0.1700
Data Index: 4963719 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19