Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6397 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.9968. Min Act: -0.1700
Data Index: 6166749 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.8718. Min Act: -0.1700
Data Index: 4656081 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.7780. Min Act: -0.1700
Data Index: 3709637 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.7780. Min Act: -0.1700
Data Index: 5572943 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.7155. Min Act: -0.1700
Data Index: 1531937 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.7155. Min Act: -0.1700
Data Index: 8410769 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.7155. Min Act: -0.1700
Data Index: 7233374 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6843. Min Act: -0.1700
Data Index: 3375942 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6843. Min Act: -0.1700
Data Index: 5769676 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6530. Min Act: -0.1700
Data Index: 8300127 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6530. Min Act: -0.1700
Data Index: 1396896 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6843. Min Act: -0.1700
Data Index: 2682874 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6530. Min Act: -0.1700
Data Index: 4485758 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6218. Min Act: -0.1700
Data Index: 3458703 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.5905. Min Act: -0.1700
Data Index: 535180 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.5905. Min Act: -0.1700
Data Index: 3738771 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.5905. Min Act: -0.1700
Data Index: 7208559 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.6218. Min Act: -0.1700
Data Index: 8118875 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.5593. Min Act: -0.1700
Data Index: 1248001 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9968. Min Range: -5.9968
Max Act: 5.5280. Min Act: -0.1700
Data Index: 7280856 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19