Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.5722. Min Act: -0.1700
Data Index: 4091462 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4784. Min Act: -0.1700
Data Index: 4948058 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4472. Min Act: -0.1700
Data Index: 7941304 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4472. Min Act: -0.1700
Data Index: 1808674 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4472. Min Act: -0.1700
Data Index: 5131852 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4159. Min Act: -0.1700
Data Index: 7403028 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4159. Min Act: -0.1700
Data Index: 1911326 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4159. Min Act: -0.1700
Data Index: 6203278 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3534. Min Act: -0.1700
Data Index: 1200547 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3534. Min Act: -0.1700
Data Index: 956530 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3534. Min Act: -0.1700
Data Index: 4956245 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3847. Min Act: -0.1700
Data Index: 7555510 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 6339274 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 4675486 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2909. Min Act: -0.1700
Data Index: 1407140 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2909. Min Act: -0.1700
Data Index: 22627 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 5913938 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2909. Min Act: -0.1700
Data Index: 2267592 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2909. Min Act: -0.1700
Data Index: 6327778 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2909. Min Act: -0.1700
Data Index: 4303092 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19