Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6072 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.6413. Min Act: -0.1700
Data Index: 5493504 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.6413. Min Act: -0.1700
Data Index: 5538435 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.6101. Min Act: -0.1700
Data Index: 7509229 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.5788. Min Act: -0.1700
Data Index: 7208545 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.4851. Min Act: -0.1700
Data Index: 3517071 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.4851. Min Act: -0.1700
Data Index: 4136686 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.4538. Min Act: -0.1700
Data Index: 3160850 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.4538. Min Act: -0.1700
Data Index: 7242576 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.4226. Min Act: -0.1700
Data Index: 6568381 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.4226. Min Act: -0.1700
Data Index: 7486534 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.3913. Min Act: -0.1700
Data Index: 136796 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.3288. Min Act: -0.1700
Data Index: 6325486 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.2976. Min Act: -0.1700
Data Index: 2100017 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.2976. Min Act: -0.1700
Data Index: 6370427 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.3288. Min Act: -0.1700
Data Index: 6275643 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.2663. Min Act: -0.1700
Data Index: 2514090 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.2351. Min Act: -0.1700
Data Index: 2801764 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.2663. Min Act: -0.1700
Data Index: 5915474 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.2663. Min Act: -0.1700
Data Index: 7703611 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6413. Min Range: -7.6413
Max Act: 7.2976. Min Act: -0.1700
Data Index: 3864500 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19