Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6360 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0347. Min Range: -7.0347
Max Act: 7.0347. Min Act: -0.1700
Data Index: 4204029 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.9722. Min Act: -0.1700
Data Index: 6393848 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.8784. Min Act: -0.1700
Data Index: 7265795 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.8784. Min Act: -0.1700
Data Index: 807059 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.8472. Min Act: -0.1700
Data Index: 1003099 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.7222. Min Act: -0.1700
Data Index: 1663880 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.7222. Min Act: -0.1700
Data Index: 5797868 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6909. Min Act: -0.1700
Data Index: 3035862 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.7222. Min Act: -0.1700
Data Index: 6334014 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6597. Min Act: -0.1700
Data Index: 5669092 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6597. Min Act: -0.1700
Data Index: 7840827 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6597. Min Act: -0.1700
Data Index: 1742308 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6597. Min Act: -0.1700
Data Index: 6476116 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6284. Min Act: -0.1700
Data Index: 5912904 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6284. Min Act: -0.1700
Data Index: 952545 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6284. Min Act: -0.1700
Data Index: 8547955 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6284. Min Act: -0.1700
Data Index: 6065953 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6284. Min Act: -0.1700
Data Index: 167075 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.5972. Min Act: -0.1700
Data Index: 1935561 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0347. Min Range: -7.0347
Max Act: 6.6284. Min Act: -0.1700
Data Index: 7508250 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19