Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 791 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.6779. Min Act: -0.1700
Data Index: 270253 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.7092. Min Act: -0.1700
Data Index: 3333651 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.6467. Min Act: -0.1700
Data Index: 4152158 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.6154. Min Act: -0.1700
Data Index: 2383553 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.6154. Min Act: -0.1700
Data Index: 1797363 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.5529. Min Act: -0.1700
Data Index: 332511 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.5842. Min Act: -0.1700
Data Index: 1111908 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.5842. Min Act: -0.1700
Data Index: 4336659 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.5217. Min Act: -0.1700
Data Index: 3863269 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4904. Min Act: -0.1700
Data Index: 2023593 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4904. Min Act: -0.1700
Data Index: 343895 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4592. Min Act: -0.1700
Data Index: 7485005 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4592. Min Act: -0.1700
Data Index: 7425749 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4592. Min Act: -0.1700
Data Index: 2048199 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4279. Min Act: -0.1700
Data Index: 6585880 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4279. Min Act: -0.1700
Data Index: 5432101 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4279. Min Act: -0.1700
Data Index: 5012290 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.3967. Min Act: -0.1700
Data Index: 2226854 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4279. Min Act: -0.1700
Data Index: 5189603 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7092. Min Range: -5.7092
Max Act: 5.4592. Min Act: -0.1700
Data Index: 5414790 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19