Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 89 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.4897. Min Act: -0.1700
Data Index: 4570732 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.4272. Min Act: -0.1700
Data Index: 6293215 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1086245 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.2397. Min Act: -0.1700
Data Index: 5652418 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.1772. Min Act: -0.1700
Data Index: 1086246 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.1459. Min Act: -0.1700
Data Index: 8198192 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.1147. Min Act: -0.1700
Data Index: 7582698 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.1147. Min Act: -0.1700
Data Index: 5079011 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.1147. Min Act: -0.1700
Data Index: 8794576 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.1147. Min Act: -0.1700
Data Index: 4354744 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0834. Min Act: -0.1700
Data Index: 7535261 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0834. Min Act: -0.1700
Data Index: 3302723 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0834. Min Act: -0.1700
Data Index: 4130727 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0522. Min Act: -0.1700
Data Index: 5817465 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0522. Min Act: -0.1700
Data Index: 6884387 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0522. Min Act: -0.1700
Data Index: 8198191 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6237918 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4897. Min Range: -6.4897
Max Act: 5.9897. Min Act: -0.1700
Data Index: 8476514 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4897. Min Range: -6.4897
Max Act: 6.0209. Min Act: -0.1700
Data Index: 21825 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4897. Min Range: -6.4897
Max Act: 5.9897. Min Act: -0.1700
Data Index: 1032739 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19