Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4360 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.6949. Min Act: -0.1700
Data Index: 7087115 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.6324. Min Act: -0.1700
Data Index: 724274 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.5387. Min Act: -0.1700
Data Index: 4993392 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.5387. Min Act: -0.1700
Data Index: 4413572 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.5387. Min Act: -0.1700
Data Index: 6691468 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.3512. Min Act: -0.1700
Data Index: 2087055 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.3824. Min Act: -0.1700
Data Index: 2272933 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.3199. Min Act: -0.1700
Data Index: 573486 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2887. Min Act: -0.1700
Data Index: 7332356 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2574. Min Act: -0.1700
Data Index: 2316403 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2574. Min Act: -0.1700
Data Index: 6573225 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2574. Min Act: -0.1700
Data Index: 1745937 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2887. Min Act: -0.1700
Data Index: 8684681 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2262. Min Act: -0.1700
Data Index: 4235657 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2262. Min Act: -0.1700
Data Index: 3626695 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.2262. Min Act: -0.1700
Data Index: 5575716 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.1949. Min Act: -0.1700
Data Index: 5949442 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.1949. Min Act: -0.1700
Data Index: 941153 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.1949. Min Act: -0.1700
Data Index: 7585888 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6949. Min Range: -5.6949
Max Act: 5.1949. Min Act: -0.1700
Data Index: 5091224 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19