Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4258 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4840. Min Act: -0.1700
Data Index: 1704863 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4528. Min Act: -0.1700
Data Index: 538276 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4528. Min Act: -0.1700
Data Index: 6197451 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4215. Min Act: -0.1700
Data Index: 8018523 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4215. Min Act: -0.1700
Data Index: 7781861 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4215. Min Act: -0.1700
Data Index: 7234537 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4528. Min Act: -0.1700
Data Index: 431038 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.4215. Min Act: -0.1700
Data Index: 625175 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.3590. Min Act: -0.1700
Data Index: 1239898 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.3590. Min Act: -0.1700
Data Index: 8455621 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.3590. Min Act: -0.1700
Data Index: 4348400 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.3590. Min Act: -0.1700
Data Index: 6233998 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.3278. Min Act: -0.1700
Data Index: 6088514 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.3278. Min Act: -0.1700
Data Index: 3311625 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.3278. Min Act: -0.1700
Data Index: 1723172 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.2965. Min Act: -0.1700
Data Index: 3958055 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.2965. Min Act: -0.1700
Data Index: 4071657 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.2965. Min Act: -0.1700
Data Index: 8288342 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.2965. Min Act: -0.1700
Data Index: 6008975 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4840. Min Range: -5.4840
Max Act: 5.2965. Min Act: -0.1700
Data Index: 5686915 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19