Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 668 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.7261. Min Act: -0.1700
Data Index: 7135471 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.6011. Min Act: -0.1700
Data Index: 221006 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.6011. Min Act: -0.1700
Data Index: 1704199 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.5386. Min Act: -0.1700
Data Index: 4581420 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.5073. Min Act: -0.1700
Data Index: 5266825 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.4761. Min Act: -0.1700
Data Index: 4102343 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.4136. Min Act: -0.1700
Data Index: 1062228 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.3823. Min Act: -0.1700
Data Index: 4753328 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.3511. Min Act: -0.1700
Data Index: 8777926 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.3511. Min Act: -0.1700
Data Index: 5033480 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.3511. Min Act: -0.1700
Data Index: 2460938 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.3198. Min Act: -0.1700
Data Index: 8332394 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.3198. Min Act: -0.1700
Data Index: 2524690 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.2886. Min Act: -0.1700
Data Index: 4334027 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.2261. Min Act: -0.1700
Data Index: 1859103 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.2261. Min Act: -0.1700
Data Index: 7577236 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.1948. Min Act: -0.1700
Data Index: 6634932 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.2573. Min Act: -0.1700
Data Index: 3971364 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.2261. Min Act: -0.1700
Data Index: 3320283 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7261. Min Range: -5.7261
Max Act: 5.2261. Min Act: -0.1700
Data Index: 7140263 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19