Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.7147. Min Act: -0.1700
Data Index: 5753746 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.5585. Min Act: -0.1700
Data Index: 958055 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.3085. Min Act: -0.1700
Data Index: 5148907 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.2772. Min Act: -0.1700
Data Index: 5379264 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.2772. Min Act: -0.1700
Data Index: 7504830 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.2460. Min Act: -0.1700
Data Index: 3305616 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1835. Min Act: -0.1700
Data Index: 445614 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1522. Min Act: -0.1700
Data Index: 3106835 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1835. Min Act: -0.1700
Data Index: 8015175 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1835. Min Act: -0.1700
Data Index: 2082663 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1835. Min Act: -0.1700
Data Index: 2763104 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1835. Min Act: -0.1700
Data Index: 2170549 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1835. Min Act: -0.1700
Data Index: 1150038 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1522. Min Act: -0.1700
Data Index: 4205535 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1522. Min Act: -0.1700
Data Index: 215390 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1210. Min Act: -0.1700
Data Index: 741537 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1210. Min Act: -0.1700
Data Index: 4768227 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1210. Min Act: -0.1700
Data Index: 5797261 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1210. Min Act: -0.1700
Data Index: 2174588 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.1210. Min Act: -0.1700
Data Index: 4170213 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19