Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4058 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3310. Min Range: -5.3310
Max Act: 5.3310. Min Act: -0.1700
Data Index: 1768968 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3310. Min Range: -5.3310
Max Act: 5.2998. Min Act: -0.1700
Data Index: 1022300 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3310. Min Range: -5.3310
Max Act: 5.1748. Min Act: -0.1700
Data Index: 2602791 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3310. Min Range: -5.3310
Max Act: 5.1123. Min Act: -0.1700
Data Index: 3053778 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3310. Min Range: -5.3310
Max Act: 5.0810. Min Act: -0.1700
Data Index: 706268 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3310. Min Range: -5.3310
Max Act: 5.0185. Min Act: -0.1700
Data Index: 2732910 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9873. Min Act: -0.1700
Data Index: 8538127 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9873. Min Act: -0.1700
Data Index: 238568 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9560. Min Act: -0.1700
Data Index: 5603607 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9560. Min Act: -0.1700
Data Index: 948080 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9560. Min Act: -0.1700
Data Index: 1029576 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9248. Min Act: -0.1700
Data Index: 4147266 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9248. Min Act: -0.1700
Data Index: 2585575 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9248. Min Act: -0.1700
Data Index: 7824597 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.8935. Min Act: -0.1700
Data Index: 5016340 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.9248. Min Act: -0.1700
Data Index: 2602794 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.8935. Min Act: -0.1700
Data Index: 2842019 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.8935. Min Act: -0.1700
Data Index: 3637853 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.8935. Min Act: -0.1700
Data Index: 5159385 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3310. Min Range: -5.3310
Max Act: 4.8935. Min Act: -0.1700
Data Index: 7026076 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19