Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.5050. Min Act: -0.1700
Data Index: 4916389 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.5675. Min Act: -0.1700
Data Index: 3811016 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.2550. Min Act: -0.1700
Data Index: 6145628 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.2550. Min Act: -0.1700
Data Index: 6465921 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.2237. Min Act: -0.1700
Data Index: 4695805 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.2237. Min Act: -0.1700
Data Index: 1247852 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.1925. Min Act: -0.1700
Data Index: 7775960 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.1925. Min Act: -0.1700
Data Index: 2419611 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.1925. Min Act: -0.1700
Data Index: 7887725 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.1612. Min Act: -0.1700
Data Index: 2152840 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.1612. Min Act: -0.1700
Data Index: 812422 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.1300. Min Act: -0.1700
Data Index: 8200430 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.1300. Min Act: -0.1700
Data Index: 1765988 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.0987. Min Act: -0.1700
Data Index: 8563233 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.0987. Min Act: -0.1700
Data Index: 3821818 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.0675. Min Act: -0.1700
Data Index: 7445657 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.0987. Min Act: -0.1700
Data Index: 3679963 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.0987. Min Act: -0.1700
Data Index: 6073440 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.0675. Min Act: -0.1700
Data Index: 4642400 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5675. Min Range: -7.5675
Max Act: 7.0675. Min Act: -0.1700
Data Index: 5497470 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19