Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 355 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3636. Min Range: -5.3636
Max Act: 5.3636. Min Act: -0.1700
Data Index: 4649024 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3636. Min Range: -5.3636
Max Act: 5.3011. Min Act: -0.1700
Data Index: 6526238 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3636. Min Range: -5.3636
Max Act: 5.0824. Min Act: -0.1700
Data Index: 5228913 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3636. Min Range: -5.3636
Max Act: 5.0199. Min Act: -0.1700
Data Index: 6118097 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3636. Min Range: -5.3636
Max Act: 5.0199. Min Act: -0.1700
Data Index: 4060920 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3636. Min Range: -5.3636
Max Act: 5.0199. Min Act: -0.1700
Data Index: 4029484 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9574. Min Act: -0.1700
Data Index: 1944111 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9886. Min Act: -0.1700
Data Index: 6876515 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9574. Min Act: -0.1700
Data Index: 7669597 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3993970 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9886. Min Act: -0.1700
Data Index: 47267 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3520440 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9574. Min Act: -0.1697
Data Index: 4936862 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9886. Min Act: -0.1700
Data Index: 5168201 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9574. Min Act: -0.1700
Data Index: 2065687 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9574. Min Act: -0.1700
Data Index: 344059 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9574. Min Act: -0.1700
Data Index: 418102 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9261. Min Act: -0.1700
Data Index: 1798109 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.8949. Min Act: -0.1700
Data Index: 548113 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3636. Min Range: -5.3636
Max Act: 4.9261. Min Act: -0.1700
Data Index: 4289013 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19