Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.6191. Min Act: -0.1636
Data Index: 5665350 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5878. Min Act: -0.1507
Data Index: 2067596 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5722. Min Act: -0.1466
Data Index: 2267407 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5565. Min Act: -0.1693
Data Index: 6052894 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5409. Min Act: -0.1335
Data Index: 2502388 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5409. Min Act: -0.1700
Data Index: 3207663 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5409. Min Act: -0.1458
Data Index: 7553222 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5409. Min Act: -0.1700
Data Index: 4336629 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5252. Min Act: -0.1593
Data Index: 7959639 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5252. Min Act: -0.1623
Data Index: 1602736 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5252. Min Act: -0.1603
Data Index: 1548154 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5252. Min Act: -0.1530
Data Index: 1362710 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5096. Min Act: -0.1696
Data Index: 7473294 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5252. Min Act: -0.1696
Data Index: 6403822 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.4939. Min Act: -0.1694
Data Index: 2531825 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5096. Min Act: -0.1698
Data Index: 691569 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5252. Min Act: -0.1549
Data Index: 2721662 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.4939. Min Act: -0.1700
Data Index: 717445 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.5096. Min Act: -0.1634
Data Index: 741761 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6191. Min Range: -3.6191
Max Act: 3.4939. Min Act: -0.1526
Data Index: 3096522 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19