Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0601. Min Range: -7.0601
Max Act: 7.0601. Min Act: -0.1700
Data Index: 1809461 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.5913. Min Act: -0.1700
Data Index: 4659366 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.5288. Min Act: -0.1700
Data Index: 8324682 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4976. Min Act: -0.1700
Data Index: 6497605 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4663. Min Act: -0.1700
Data Index: 4872936 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4663. Min Act: -0.1700
Data Index: 4997389 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4351. Min Act: -0.1700
Data Index: 1099496 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4351. Min Act: -0.1700
Data Index: 4853723 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4351. Min Act: -0.1700
Data Index: 5284193 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4038. Min Act: -0.1700
Data Index: 8122803 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4038. Min Act: -0.1700
Data Index: 1382873 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.4038. Min Act: -0.1700
Data Index: 8290507 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.2788. Min Act: -0.1700
Data Index: 5650322 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.2163. Min Act: -0.1700
Data Index: 2332347 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.2476. Min Act: -0.1700
Data Index: 3107895 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.2163. Min Act: -0.1700
Data Index: 3528104 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.2163. Min Act: -0.1700
Data Index: 1060049 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.1538. Min Act: -0.1700
Data Index: 8831351 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.1538. Min Act: -0.1700
Data Index: 2582821 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0601. Min Range: -7.0601
Max Act: 6.1226. Min Act: -0.1700
Data Index: 2710723 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19