Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.4193. Min Act: -0.1700
Data Index: 801111 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.3256. Min Act: -0.1700
Data Index: 3135962 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.2631. Min Act: -0.1700
Data Index: 1208407 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.2318. Min Act: -0.1700
Data Index: 6510613 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.2318. Min Act: -0.1700
Data Index: 3042340 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1693. Min Act: -0.1700
Data Index: 7711716 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1693. Min Act: -0.1700
Data Index: 6889316 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 5000825 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 4514026 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 5482500 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 7702550 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1693. Min Act: -0.1700
Data Index: 1320906 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 1464510 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 4843793 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 1658123 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1381. Min Act: -0.1700
Data Index: 5145662 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1068. Min Act: -0.1700
Data Index: 1832850 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1068. Min Act: -0.1700
Data Index: 4431849 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.1068. Min Act: -0.1700
Data Index: 2458705 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4193. Min Range: -4.4193
Max Act: 4.0755. Min Act: -0.1700
Data Index: 6600515 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19