Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6283 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.6866. Min Act: -0.1700
Data Index: 7322669 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.4678. Min Act: -0.1700
Data Index: 6817622 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.4053. Min Act: -0.1700
Data Index: 4906601 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.3741. Min Act: -0.1700
Data Index: 6973204 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.3116. Min Act: -0.1700
Data Index: 1213916 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.2178. Min Act: -0.1700
Data Index: 7887681 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.2178. Min Act: -0.1700
Data Index: 6442078 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.2178. Min Act: -0.1700
Data Index: 8243429 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1865. Min Act: -0.1700
Data Index: 5150 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1865. Min Act: -0.1700
Data Index: 1228399 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1865. Min Act: -0.1700
Data Index: 2556676 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1553. Min Act: -0.1700
Data Index: 2903377 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1240. Min Act: -0.1700
Data Index: 454895 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1553. Min Act: -0.1700
Data Index: 5478646 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1240. Min Act: -0.1700
Data Index: 5968215 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1240. Min Act: -0.1700
Data Index: 1398495 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1240. Min Act: -0.1700
Data Index: 2019521 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1240. Min Act: -0.1700
Data Index: 2756720 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1240. Min Act: -0.1700
Data Index: 1426233 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6866. Min Range: -4.6866
Max Act: 4.1240. Min Act: -0.1700
Data Index: 6123084 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19