Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3300. Min Range: -7.3300
Max Act: 7.3300. Min Act: -0.1700
Data Index: 4020283 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3300. Min Range: -7.3300
Max Act: 7.1425. Min Act: -0.1700
Data Index: 5026262 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3300. Min Range: -7.3300
Max Act: 7.0488. Min Act: -0.1700
Data Index: 8698512 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3300. Min Range: -7.3300
Max Act: 7.0175. Min Act: -0.1700
Data Index: 5530914 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.9238. Min Act: -0.1700
Data Index: 1780969 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.8925. Min Act: -0.1700
Data Index: 8329323 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.9238. Min Act: -0.1700
Data Index: 915982 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.8925. Min Act: -0.1700
Data Index: 2510153 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.8613. Min Act: -0.1700
Data Index: 1541460 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.8613. Min Act: -0.1700
Data Index: 803451 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.8300. Min Act: -0.1700
Data Index: 2995599 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.8300. Min Act: -0.1700
Data Index: 1444462 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7988. Min Act: -0.1700
Data Index: 7239907 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7675. Min Act: -0.1700
Data Index: 7194880 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7675. Min Act: -0.1700
Data Index: 1349160 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7675. Min Act: -0.1700
Data Index: 6450232 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7050. Min Act: -0.1700
Data Index: 8808219 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7363. Min Act: -0.1700
Data Index: 4439491 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7050. Min Act: -0.1700
Data Index: 5069413 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3300. Min Range: -7.3300
Max Act: 6.7050. Min Act: -0.1700
Data Index: 5197437 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19