Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4690 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.5290. Min Act: -0.1700
Data Index: 8047201 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4665. Min Act: -0.1700
Data Index: 2961766 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4353. Min Act: -0.1700
Data Index: 417765 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4353. Min Act: -0.1700
Data Index: 6154368 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4353. Min Act: -0.1700
Data Index: 8047196 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 3770072 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 7267355 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3728. Min Act: -0.1700
Data Index: 2214612 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 5645998 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 2079087 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 303254 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 7842805 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 741600 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 5882392 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 7318085 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3103. Min Act: -0.1700
Data Index: 6925962 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 8826731 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 1129732 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3103. Min Act: -0.1700
Data Index: 6356971 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3103. Min Act: -0.1700
Data Index: 6881867 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19