Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7014. Min Range: -6.7014
Max Act: 6.7014. Min Act: -0.1700
Data Index: 4954335 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7014. Min Range: -6.7014
Max Act: 6.4514. Min Act: -0.1700
Data Index: 39628 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7014. Min Range: -6.7014
Max Act: 6.2326. Min Act: -0.1700
Data Index: 7373954 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7014. Min Range: -6.7014
Max Act: 6.2326. Min Act: -0.1700
Data Index: 436985 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7014. Min Range: -6.7014
Max Act: 6.1701. Min Act: -0.1700
Data Index: 1565681 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7014. Min Range: -6.7014
Max Act: 6.1076. Min Act: -0.1700
Data Index: 7052285 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7014. Min Range: -6.7014
Max Act: 6.0764. Min Act: -0.1700
Data Index: 4707701 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4489944 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.9826. Min Act: -0.1700
Data Index: 1342512 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.9826. Min Act: -0.1700
Data Index: 5155398 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.9201. Min Act: -0.1700
Data Index: 2174591 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.8889. Min Act: -0.1700
Data Index: 12479 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.8889. Min Act: -0.1700
Data Index: 5191538 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.8576. Min Act: -0.1700
Data Index: 3239952 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.8264. Min Act: -0.1700
Data Index: 3082652 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.8264. Min Act: -0.1700
Data Index: 7300428 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.7951. Min Act: -0.1700
Data Index: 1522424 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.7951. Min Act: -0.1700
Data Index: 3064912 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.7639. Min Act: -0.1700
Data Index: 3779817 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7014. Min Range: -6.7014
Max Act: 5.7639. Min Act: -0.1700
Data Index: 5280877 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19