Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 600 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.5409. Min Act: -0.1700
Data Index: 1399948 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.5722. Min Act: -0.1700
Data Index: 5015650 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.5409. Min Act: -0.1700
Data Index: 4124476 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.5722. Min Act: -0.1700
Data Index: 3807727 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.4784. Min Act: -0.1700
Data Index: 6108780 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.4472. Min Act: -0.1700
Data Index: 5167436 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.4472. Min Act: -0.1700
Data Index: 3197579 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.4159. Min Act: -0.1700
Data Index: 6862418 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.4159. Min Act: -0.1700
Data Index: 3112801 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.3534. Min Act: -0.1700
Data Index: 5279159 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.3534. Min Act: -0.1700
Data Index: 265501 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.3534. Min Act: -0.1700
Data Index: 6860307 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.3222. Min Act: -0.1700
Data Index: 572949 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.3222. Min Act: -0.1700
Data Index: 3543595 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.3222. Min Act: -0.1700
Data Index: 2246229 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.2597. Min Act: -0.1700
Data Index: 5805687 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.2909. Min Act: -0.1700
Data Index: 6808971 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.2909. Min Act: -0.1700
Data Index: 1912264 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.2909. Min Act: -0.1700
Data Index: 314460 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5722. Min Range: -5.5722
Max Act: 5.2909. Min Act: -0.1700
Data Index: 1544602 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19