Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.8326. Min Act: -0.1700
Data Index: 4548777 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.5514. Min Act: -0.1700
Data Index: 5142484 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.3951. Min Act: -0.1700
Data Index: 5217844 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.3639. Min Act: -0.1700
Data Index: 5990159 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.2701. Min Act: -0.1700
Data Index: 4054454 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.2701. Min Act: -0.1700
Data Index: 329191 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.2701. Min Act: -0.1700
Data Index: 32855 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.3014. Min Act: -0.1700
Data Index: 3807446 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.2701. Min Act: -0.1700
Data Index: 6833421 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.2701. Min Act: -0.1700
Data Index: 4054457 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1764. Min Act: -0.1700
Data Index: 5135921 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1764. Min Act: -0.1700
Data Index: 2929677 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1451. Min Act: -0.1700
Data Index: 5723903 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1139. Min Act: -0.1700
Data Index: 3668826 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1139. Min Act: -0.1700
Data Index: 2283509 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1139. Min Act: -0.1700
Data Index: 2047363 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1139. Min Act: -0.1700
Data Index: 206048 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.1139. Min Act: -0.1700
Data Index: 6393794 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.0826. Min Act: -0.1700
Data Index: 5716863 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8326. Min Range: -6.8326
Max Act: 6.0826. Min Act: -0.1700
Data Index: 2007006 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19