Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2244 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1791. Min Range: -8.1791
Max Act: 8.1791. Min Act: -0.1700
Data Index: 8566925 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1791. Min Range: -8.1791
Max Act: 8.1166. Min Act: -0.1700
Data Index: 4497200 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1791. Min Range: -8.1791
Max Act: 8.0541. Min Act: -0.1700
Data Index: 7813141 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.9291. Min Act: -0.1700
Data Index: 8566926 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.9291. Min Act: -0.1700
Data Index: 1542642 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.8666. Min Act: -0.1700
Data Index: 5801387 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.8666. Min Act: -0.1700
Data Index: 55845 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.8041. Min Act: -0.1700
Data Index: 2613630 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.8041. Min Act: -0.1700
Data Index: 6590462 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.8041. Min Act: -0.1700
Data Index: 4111910 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.8041. Min Act: -0.1700
Data Index: 3952310 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.7416. Min Act: -0.1700
Data Index: 7887081 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.6791. Min Act: -0.1700
Data Index: 791585 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.6166. Min Act: -0.1700
Data Index: 4502264 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.6791. Min Act: -0.1700
Data Index: 2558757 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.6166. Min Act: -0.1700
Data Index: 6357681 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.5541. Min Act: -0.1700
Data Index: 7935586 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.5854. Min Act: -0.1700
Data Index: 8494510 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.5541. Min Act: -0.1700
Data Index: 8315077 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1791. Min Range: -8.1791
Max Act: 7.5541. Min Act: -0.1700
Data Index: 1255222 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19