Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2001 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1740. Min Range: -6.1740
Max Act: 6.1740. Min Act: -0.1700
Data Index: 1033192 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.9865. Min Act: -0.1700
Data Index: 7951813 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.9552. Min Act: -0.1700
Data Index: 3259374 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 7231747 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 1813718 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.8302. Min Act: -0.1700
Data Index: 4613647 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7990. Min Act: -0.1700
Data Index: 3397828 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7677. Min Act: -0.1700
Data Index: 4169185 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7677. Min Act: -0.1700
Data Index: 2242021 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7365. Min Act: -0.1700
Data Index: 6656706 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7052. Min Act: -0.1700
Data Index: 7675474 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.7052. Min Act: -0.1700
Data Index: 3712607 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.6427. Min Act: -0.1700
Data Index: 5380204 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.6427. Min Act: -0.1700
Data Index: 2493721 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.6115. Min Act: -0.1700
Data Index: 855675 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.6115. Min Act: -0.1700
Data Index: 7927247 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.5802. Min Act: -0.1700
Data Index: 6588238 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.6115. Min Act: -0.1700
Data Index: 4284353 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.5490. Min Act: -0.1700
Data Index: 2964954 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1740. Min Range: -6.1740
Max Act: 5.5490. Min Act: -0.1700
Data Index: 2686538 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19