Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1740 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.4940. Min Act: -0.1700
Data Index: 1481849 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.4002. Min Act: -0.1700
Data Index: 1857075 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.4002. Min Act: -0.1700
Data Index: 7618 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.3690. Min Act: -0.1700
Data Index: 5129631 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.3377. Min Act: -0.1700
Data Index: 368651 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.3065. Min Act: -0.1700
Data Index: 6162558 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.3065. Min Act: -0.1700
Data Index: 8680928 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.3065. Min Act: -0.1700
Data Index: 2695272 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2440. Min Act: -0.1700
Data Index: 549983 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2440. Min Act: -0.1700
Data Index: 1869216 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1815. Min Act: -0.1700
Data Index: 5721574 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2127. Min Act: -0.1700
Data Index: 188652 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2127. Min Act: -0.1700
Data Index: 3590874 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1815. Min Act: -0.1700
Data Index: 675695 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1190. Min Act: -0.1700
Data Index: 452543 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1815. Min Act: -0.1700
Data Index: 1169811 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1815. Min Act: -0.1700
Data Index: 4053222 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1502. Min Act: -0.1700
Data Index: 3827385 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1502. Min Act: -0.1700
Data Index: 5721575 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1815. Min Act: -0.1700
Data Index: 5903668 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19