Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5227 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.4458. Min Act: -0.1700
Data Index: 5397177 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.4458. Min Act: -0.1700
Data Index: 8133112 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.4145. Min Act: -0.1700
Data Index: 3703893 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.4145. Min Act: -0.1700
Data Index: 5713994 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.4145. Min Act: -0.1700
Data Index: 7768158 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3833. Min Act: -0.1700
Data Index: 8148433 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3833. Min Act: -0.1700
Data Index: 3295884 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3520. Min Act: -0.1700
Data Index: 8148432 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3520. Min Act: -0.1700
Data Index: 8799408 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3208. Min Act: -0.1700
Data Index: 7662689 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3520. Min Act: -0.1700
Data Index: 1488975 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.2895. Min Act: -0.1700
Data Index: 510662 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3208. Min Act: -0.1700
Data Index: 5715331 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.2895. Min Act: -0.1700
Data Index: 2526848 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3208. Min Act: -0.1700
Data Index: 1260879 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3520. Min Act: -0.1700
Data Index: 2582217 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3208. Min Act: -0.1700
Data Index: 6979479 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.3208. Min Act: -0.1700
Data Index: 8521531 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.2895. Min Act: -0.1700
Data Index: 3115228 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4458. Min Range: -5.4458
Max Act: 5.2895. Min Act: -0.1700
Data Index: 3248685 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19