Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 637 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.8524. Min Act: -0.1700
Data Index: 4520520 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5805. Min Act: -0.1700
Data Index: 2731824 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.6127. Min Act: -0.1700
Data Index: 8227288 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5644. Min Act: -0.1700
Data Index: 3336939 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5644. Min Act: -0.1700
Data Index: 1433686 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5644. Min Act: -0.1700
Data Index: 7861805 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5644. Min Act: -0.1700
Data Index: 532488 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5644. Min Act: -0.1700
Data Index: 7207247 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5483. Min Act: -0.1700
Data Index: 6383406 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5483. Min Act: -0.1700
Data Index: 4543120 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5159. Min Act: -0.1700
Data Index: 3723570 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5159. Min Act: -0.1700
Data Index: 3093323 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.5159. Min Act: -0.1700
Data Index: 6895206 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.4998. Min Act: -0.1700
Data Index: 1335576 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.4835. Min Act: -0.1700
Data Index: 4935698 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.4998. Min Act: -0.1700
Data Index: 7443271 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.4998. Min Act: -0.1700
Data Index: 7605195 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.4835. Min Act: -0.1700
Data Index: 1663912 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.4998. Min Act: -0.1700
Data Index: 6744960 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8524. Min Range: -2.8524
Max Act: 2.4998. Min Act: -0.1700
Data Index: 6819806 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19