Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3743 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.6608. Min Act: -0.1700
Data Index: 1492643 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.6296. Min Act: -0.1700
Data Index: 6033888 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.4421. Min Act: -0.1700
Data Index: 4359162 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.4108. Min Act: -0.1700
Data Index: 2328446 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.4108. Min Act: -0.1700
Data Index: 2982709 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.3796. Min Act: -0.1700
Data Index: 7964164 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.3796. Min Act: -0.1700
Data Index: 6736644 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.3483. Min Act: -0.1700
Data Index: 1113509 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.3483. Min Act: -0.1700
Data Index: 7178559 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.2858. Min Act: -0.1700
Data Index: 964628 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.2546. Min Act: -0.1700
Data Index: 1246541 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.1921. Min Act: -0.1700
Data Index: 5325668 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.2233. Min Act: -0.1700
Data Index: 3539535 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.2233. Min Act: -0.1700
Data Index: 6642822 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.2233. Min Act: -0.1700
Data Index: 4586250 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.1921. Min Act: -0.1700
Data Index: 8388906 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.1921. Min Act: -0.1700
Data Index: 959882 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.1921. Min Act: -0.1700
Data Index: 1117934 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.1608. Min Act: -0.1700
Data Index: 979268 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6608. Min Range: -5.6608
Max Act: 5.1296. Min Act: -0.1700
Data Index: 6753436 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19