Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.9337. Min Act: -0.1700
Data Index: 5741094 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.9024. Min Act: -0.1700
Data Index: 1314578 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.8712. Min Act: -0.1700
Data Index: 134627 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.8399. Min Act: -0.1700
Data Index: 1298274 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.7774. Min Act: -0.1700
Data Index: 4016472 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.7774. Min Act: -0.1700
Data Index: 3337052 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.7462. Min Act: -0.1700
Data Index: 4702762 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.7462. Min Act: -0.1700
Data Index: 2755284 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.7462. Min Act: -0.1700
Data Index: 7807009 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.7149. Min Act: -0.1700
Data Index: 7753424 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.7149. Min Act: -0.1700
Data Index: 273697 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.6524. Min Act: -0.1700
Data Index: 783117 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.6837. Min Act: -0.1700
Data Index: 4032667 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.6524. Min Act: -0.1700
Data Index: 2355746 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.6524. Min Act: -0.1700
Data Index: 3125029 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.6212. Min Act: -0.1700
Data Index: 3195434 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.6212. Min Act: -0.1700
Data Index: 2547612 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.6212. Min Act: -0.1700
Data Index: 8328850 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.5899. Min Act: -0.1700
Data Index: 7678873 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9337. Min Range: -4.9337
Max Act: 4.5899. Min Act: -0.1700
Data Index: 2252494 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19