Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.4364. Min Act: -0.1700
Data Index: 7418549 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.2176. Min Act: -0.1700
Data Index: 2118181 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.2489. Min Act: -0.1700
Data Index: 1212821 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.2489. Min Act: -0.1700
Data Index: 2742846 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.2176. Min Act: -0.1700
Data Index: 2750967 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.1551. Min Act: -0.1700
Data Index: 5461104 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.1239. Min Act: -0.1700
Data Index: 6888374 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0926. Min Act: -0.1700
Data Index: 1091000 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0926. Min Act: -0.1700
Data Index: 1863965 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0926. Min Act: -0.1700
Data Index: 7193380 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0614. Min Act: -0.1700
Data Index: 1240098 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0926. Min Act: -0.1699
Data Index: 7616164 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 8353686 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 5703245 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 459842 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 6621052 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 3589319 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 7945565 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 7789820 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4364. Min Range: -6.4364
Max Act: 6.0301. Min Act: -0.1700
Data Index: 1073069 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19