Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.6815. Min Act: -0.1700
Data Index: 1830142 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.6815. Min Act: -0.1700
Data Index: 6642815 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.2440. Min Act: -0.1700
Data Index: 7621552 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.3065. Min Act: -0.1700
Data Index: 407151 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.3065. Min Act: -0.1700
Data Index: 2410146 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.2440. Min Act: -0.1700
Data Index: 5258357 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.1502. Min Act: -0.1700
Data Index: 7704111 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.1502. Min Act: -0.1700
Data Index: 5106217 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.1190. Min Act: -0.1700
Data Index: 1506761 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.0565. Min Act: -0.1700
Data Index: 6227290 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9940. Min Act: -0.1700
Data Index: 823565 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6815. Min Range: -7.6815
Max Act: 7.0252. Min Act: -0.1700
Data Index: 8414780 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9627. Min Act: -0.1700
Data Index: 1784792 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9627. Min Act: -0.1700
Data Index: 6796188 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9627. Min Act: -0.1700
Data Index: 3141180 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9627. Min Act: -0.1700
Data Index: 2130618 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9315. Min Act: -0.1700
Data Index: 5883773 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9315. Min Act: -0.1700
Data Index: 2013114 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9002. Min Act: -0.1700
Data Index: 2940687 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6815. Min Range: -7.6815
Max Act: 6.9315. Min Act: -0.1700
Data Index: 6955511 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19