Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.8820. Min Act: -0.1700
Data Index: 6200128 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.8195. Min Act: -0.1700
Data Index: 7779065 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6945. Min Act: -0.1700
Data Index: 7489588 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6945. Min Act: -0.1700
Data Index: 1266398 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6633. Min Act: -0.1700
Data Index: 1516679 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6320. Min Act: -0.1700
Data Index: 711926 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6320. Min Act: -0.1700
Data Index: 7074174 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6320. Min Act: -0.1700
Data Index: 993383 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6008. Min Act: -0.1700
Data Index: 7095160 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5695. Min Act: -0.1700
Data Index: 926940 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6008. Min Act: -0.1700
Data Index: 5370873 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5695. Min Act: -0.1700
Data Index: 7173735 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6008. Min Act: -0.1700
Data Index: 2873780 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.6008. Min Act: -0.1700
Data Index: 4413180 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5383. Min Act: -0.1700
Data Index: 7001088 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5383. Min Act: -0.1700
Data Index: 1332440 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5383. Min Act: -0.1700
Data Index: 3021888 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5383. Min Act: -0.1700
Data Index: 5260907 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5383. Min Act: -0.1700
Data Index: 3990062 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8820. Min Range: -5.8820
Max Act: 5.5383. Min Act: -0.1700
Data Index: 536729 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19