Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.8536. Min Act: -0.1700
Data Index: 2472115 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.8223. Min Act: -0.1700
Data Index: 7840794 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.6503. Min Act: -0.1700
Data Index: 4319306 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.5877. Min Act: -0.1700
Data Index: 1271889 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.5564. Min Act: -0.1700
Data Index: 4386433 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.5407. Min Act: -0.1700
Data Index: 5031514 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.5251. Min Act: -0.1700
Data Index: 2624701 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.4937. Min Act: -0.1700
Data Index: 5587909 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.4937. Min Act: -0.1700
Data Index: 7235310 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.4467. Min Act: -0.1700
Data Index: 4885939 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.4311. Min Act: -0.1700
Data Index: 1097494 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.4311. Min Act: -0.1700
Data Index: 1995371 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.3997. Min Act: -0.1700
Data Index: 6462820 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.3997. Min Act: -0.1700
Data Index: 5897821 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.4154. Min Act: -0.1700
Data Index: 6664810 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.4154. Min Act: -0.1700
Data Index: 3867135 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.3997. Min Act: -0.1700
Data Index: 4056927 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.3997. Min Act: -0.1700
Data Index: 7901791 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.3997. Min Act: -0.1700
Data Index: 4556209 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8536. Min Range: -3.8536
Max Act: 3.3683. Min Act: -0.1700
Data Index: 2281562 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19