Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1041 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.7693. Min Act: -0.1700
Data Index: 2096097 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.7380. Min Act: -0.1700
Data Index: 3062566 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.6130. Min Act: -0.1700
Data Index: 274985 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5580934 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.6443. Min Act: -0.1700
Data Index: 8277521 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.6130. Min Act: -0.1700
Data Index: 6019343 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.5818. Min Act: -0.1700
Data Index: 3062565 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.5505. Min Act: -0.1700
Data Index: 4252121 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.5193. Min Act: -0.1700
Data Index: 3956692 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4880. Min Act: -0.1700
Data Index: 1183569 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.5193. Min Act: -0.1700
Data Index: 7521716 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4568. Min Act: -0.1700
Data Index: 5008781 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4568. Min Act: -0.1700
Data Index: 8814678 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4568. Min Act: -0.1700
Data Index: 4028143 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4568. Min Act: -0.1700
Data Index: 3198130 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4568. Min Act: -0.1700
Data Index: 3732538 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4568. Min Act: -0.1700
Data Index: 5172769 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4255. Min Act: -0.1700
Data Index: 5413872 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.4255. Min Act: -0.1700
Data Index: 6287742 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7693. Min Range: -5.7693
Max Act: 5.3630. Min Act: -0.1700
Data Index: 6218646 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19