Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3184 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1357. Min Range: -6.1357
Max Act: 6.1357. Min Act: -0.1700
Data Index: 3438590 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1357. Min Range: -6.1357
Max Act: 6.0420. Min Act: -0.1700
Data Index: 4659680 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1357. Min Range: -6.1357
Max Act: 6.0107. Min Act: -0.1700
Data Index: 4393874 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1357. Min Range: -6.1357
Max Act: 6.0107. Min Act: -0.1700
Data Index: 6472557 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1357. Min Range: -6.1357
Max Act: 6.0107. Min Act: -0.1700
Data Index: 876748 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1357. Min Range: -6.1357
Max Act: 6.0107. Min Act: -0.1700
Data Index: 6602516 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.9482. Min Act: -0.1700
Data Index: 3138237 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.9795. Min Act: -0.1700
Data Index: 6615372 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.9170. Min Act: -0.1700
Data Index: 634569 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.9170. Min Act: -0.1700
Data Index: 3656046 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.8857. Min Act: -0.1700
Data Index: 6625716 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.8857. Min Act: -0.1700
Data Index: 1648228 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.8857. Min Act: -0.1700
Data Index: 6983496 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.8545. Min Act: -0.1700
Data Index: 377076 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.8232. Min Act: -0.1700
Data Index: 1582256 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.8232. Min Act: -0.1700
Data Index: 3504686 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.8545. Min Act: -0.1700
Data Index: 6339883 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.7920. Min Act: -0.1700
Data Index: 3566001 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.7607. Min Act: -0.1700
Data Index: 4557481 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1357. Min Range: -6.1357
Max Act: 5.7920. Min Act: -0.1700
Data Index: 8382319 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19