Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0475. Min Range: -6.0475
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1251739 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.6100. Min Act: -0.1700
Data Index: 7141951 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.5788. Min Act: -0.1700
Data Index: 1932835 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.5788. Min Act: -0.1700
Data Index: 2834051 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.4538. Min Act: -0.1700
Data Index: 8130010 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.4538. Min Act: -0.1700
Data Index: 2224238 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.4225. Min Act: -0.1700
Data Index: 7731260 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3913. Min Act: -0.1700
Data Index: 8698210 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3913. Min Act: -0.1700
Data Index: 1446642 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3600. Min Act: -0.1700
Data Index: 7485854 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3600. Min Act: -0.1700
Data Index: 2032286 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3288. Min Act: -0.1700
Data Index: 1400911 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3600. Min Act: -0.1700
Data Index: 5950716 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3288. Min Act: -0.1700
Data Index: 3478919 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.3288. Min Act: -0.1700
Data Index: 456823 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.2663. Min Act: -0.1700
Data Index: 1921279 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.2663. Min Act: -0.1700
Data Index: 3658183 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.2663. Min Act: -0.1700
Data Index: 6493808 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.2350. Min Act: -0.1700
Data Index: 7860181 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.2350. Min Act: -0.1700
Data Index: 4666696 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19