Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4065. Min Range: -7.4065
Max Act: 7.4065. Min Act: -0.1700
Data Index: 5104689 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4065. Min Range: -7.4065
Max Act: 7.3440. Min Act: -0.1700
Data Index: 4954502 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4065. Min Range: -7.4065
Max Act: 7.3440. Min Act: -0.1700
Data Index: 4954512 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4065. Min Range: -7.4065
Max Act: 7.1877. Min Act: -0.1700
Data Index: 42254 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4065. Min Range: -7.4065
Max Act: 7.0002. Min Act: -0.1700
Data Index: 5820820 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.9377. Min Act: -0.1700
Data Index: 8110578 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.9377. Min Act: -0.1700
Data Index: 7174858 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.8752. Min Act: -0.1700
Data Index: 7689431 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.8440. Min Act: -0.1700
Data Index: 100918 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.9065. Min Act: -0.1700
Data Index: 2988871 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.7190. Min Act: -0.1700
Data Index: 5256056 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.7190. Min Act: -0.1700
Data Index: 2949895 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.6877. Min Act: -0.1700
Data Index: 2550547 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.6565. Min Act: -0.1700
Data Index: 2857588 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.6877. Min Act: -0.1700
Data Index: 8221724 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.6565. Min Act: -0.1700
Data Index: 4872803 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.5940. Min Act: -0.1700
Data Index: 2550544 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.6252. Min Act: -0.1700
Data Index: 1671550 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.6565. Min Act: -0.1700
Data Index: 7841240 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4065. Min Range: -7.4065
Max Act: 6.5940. Min Act: -0.1700
Data Index: 6726486 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19