Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2507. Min Range: -7.2507
Max Act: 7.2507. Min Act: -0.1700
Data Index: 1951170 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2507. Min Range: -7.2507
Max Act: 7.1570. Min Act: -0.1700
Data Index: 3651635 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2507. Min Range: -7.2507
Max Act: 7.0632. Min Act: -0.1700
Data Index: 7370628 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2507. Min Range: -7.2507
Max Act: 7.0007. Min Act: -0.1700
Data Index: 4203562 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.7507. Min Act: -0.1700
Data Index: 7469826 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.7195. Min Act: -0.1700
Data Index: 4636667 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.6882. Min Act: -0.1700
Data Index: 165129 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.6570. Min Act: -0.1700
Data Index: 7131596 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.5320. Min Act: -0.1700
Data Index: 4676703 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.5320. Min Act: -0.1700
Data Index: 4401525 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.5007. Min Act: -0.1700
Data Index: 969606 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.5320. Min Act: -0.1700
Data Index: 1448449 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.5007. Min Act: -0.1700
Data Index: 1244271 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.4382. Min Act: -0.1700
Data Index: 8662299 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.4695. Min Act: -0.1700
Data Index: 1961289 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.4382. Min Act: -0.1700
Data Index: 6494157 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 4841732 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 1207297 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.3445. Min Act: -0.1700
Data Index: 6663884 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2507. Min Range: -7.2507
Max Act: 6.3757. Min Act: -0.1700
Data Index: 1530800 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19