Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 553 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.7236. Min Act: -0.1700
Data Index: 7004704 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.6924. Min Act: -0.1700
Data Index: 285277 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.6299. Min Act: -0.1700
Data Index: 7004707 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.6299. Min Act: -0.1700
Data Index: 6534998 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.5674. Min Act: -0.1700
Data Index: 6541577 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.5674. Min Act: -0.1700
Data Index: 6534993 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.5049. Min Act: -0.1700
Data Index: 4048829 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.5049. Min Act: -0.1700
Data Index: 3736759 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4736. Min Act: -0.1700
Data Index: 7332465 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4736. Min Act: -0.1700
Data Index: 6378254 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4736. Min Act: -0.1700
Data Index: 7004701 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4424. Min Act: -0.1700
Data Index: 1556126 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4424. Min Act: -0.1700
Data Index: 2637481 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.3799. Min Act: -0.1700
Data Index: 4571462 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4111. Min Act: -0.1700
Data Index: 95798 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.3799. Min Act: -0.1700
Data Index: 6235744 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4111. Min Act: -0.1700
Data Index: 5553445 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.4424. Min Act: -0.1700
Data Index: 7106455 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.3799. Min Act: -0.1700
Data Index: 2116801 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7236. Min Range: -4.7236
Max Act: 4.3486. Min Act: -0.1700
Data Index: 6582731 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19