Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1091 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2227. Min Range: -7.2227
Max Act: 7.1915. Min Act: -0.1700
Data Index: 4069751 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2227. Min Range: -7.2227
Max Act: 7.2227. Min Act: -0.1700
Data Index: 2134293 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2227. Min Range: -7.2227
Max Act: 7.1602. Min Act: -0.1700
Data Index: 3299952 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2227. Min Range: -7.2227
Max Act: 7.1290. Min Act: -0.1700
Data Index: 2508338 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2227. Min Range: -7.2227
Max Act: 7.0977. Min Act: -0.1700
Data Index: 4527724 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2227. Min Range: -7.2227
Max Act: 7.0977. Min Act: -0.1700
Data Index: 6067604 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2227. Min Range: -7.2227
Max Act: 7.0040. Min Act: -0.1700
Data Index: 2418332 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.9727. Min Act: -0.1700
Data Index: 7241402 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.9727. Min Act: -0.1700
Data Index: 804402 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.9415. Min Act: -0.1700
Data Index: 802313 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.9727. Min Act: -0.1700
Data Index: 1102248 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.9415. Min Act: -0.1700
Data Index: 5407373 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.9102. Min Act: -0.1700
Data Index: 4385387 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.8790. Min Act: -0.1700
Data Index: 2434014 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.9102. Min Act: -0.1700
Data Index: 8283817 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.8790. Min Act: -0.1700
Data Index: 4779215 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.8477. Min Act: -0.1700
Data Index: 257471 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.8477. Min Act: -0.1700
Data Index: 7771751 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.8165. Min Act: -0.1700
Data Index: 5128803 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2227. Min Range: -7.2227
Max Act: 6.8165. Min Act: -0.1700
Data Index: 7616861 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19