Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4187 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0327. Min Range: -7.0327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 102165 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.8765. Min Act: -0.1700
Data Index: 7052716 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.8452. Min Act: -0.1700
Data Index: 7627278 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.7515. Min Act: -0.1700
Data Index: 6576575 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.7202. Min Act: -0.1700
Data Index: 3032325 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.6890. Min Act: -0.1700
Data Index: 8771444 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.6577. Min Act: -0.1700
Data Index: 170331 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.6577. Min Act: -0.1700
Data Index: 262845 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.6577. Min Act: -0.1700
Data Index: 8740028 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.6577. Min Act: -0.1700
Data Index: 8693904 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5640. Min Act: -0.1700
Data Index: 4685778 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5952. Min Act: -0.1700
Data Index: 4823202 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5952. Min Act: -0.1700
Data Index: 1191786 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5952. Min Act: -0.1700
Data Index: 4897781 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5640. Min Act: -0.1700
Data Index: 6772405 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5640. Min Act: -0.1700
Data Index: 8043359 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5327. Min Act: -0.1700
Data Index: 4640122 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5327. Min Act: -0.1700
Data Index: 816071 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5015. Min Act: -0.1700
Data Index: 1079794 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0327. Min Range: -7.0327
Max Act: 6.5015. Min Act: -0.1700
Data Index: 8646696 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19