Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1170. Min Range: -5.1170
Max Act: 5.1170. Min Act: -0.1700
Data Index: 8106579 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1170. Min Range: -5.1170
Max Act: 5.0545. Min Act: -0.1700
Data Index: 1368167 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.9295. Min Act: -0.1700
Data Index: 3297405 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8983. Min Act: -0.1700
Data Index: 1115789 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8358. Min Act: -0.1700
Data Index: 4322099 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8670. Min Act: -0.1700
Data Index: 2429204 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8670. Min Act: -0.1700
Data Index: 5852201 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8045. Min Act: -0.1700
Data Index: 2080694 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8358. Min Act: -0.1700
Data Index: 5477297 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8358. Min Act: -0.1700
Data Index: 7579972 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8358. Min Act: -0.1700
Data Index: 8505873 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8358. Min Act: -0.1700
Data Index: 5225290 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8358. Min Act: -0.1700
Data Index: 6424667 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8358. Min Act: -0.1700
Data Index: 1146487 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8045. Min Act: -0.1700
Data Index: 7438046 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8045. Min Act: -0.1700
Data Index: 8413593 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8045. Min Act: -0.1700
Data Index: 5016221 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.7733. Min Act: -0.1700
Data Index: 7451913 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8045. Min Act: -0.1700
Data Index: 1967338 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1170. Min Range: -5.1170
Max Act: 4.8045. Min Act: -0.1700
Data Index: 3087981 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19