Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1625 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.9156. Min Act: -0.1700
Data Index: 4165742 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.8687. Min Act: -0.1700
Data Index: 7042140 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.8531. Min Act: -0.1700
Data Index: 1204905 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.8687. Min Act: -0.1700
Data Index: 294208 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.8218. Min Act: -0.1700
Data Index: 3122354 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7905. Min Act: -0.1700
Data Index: 5051121 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7905. Min Act: -0.1700
Data Index: 4837024 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.8061. Min Act: -0.1700
Data Index: 3014940 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7905. Min Act: -0.1700
Data Index: 3354849 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7592. Min Act: -0.1700
Data Index: 972162 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7280. Min Act: -0.1700
Data Index: 7668776 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7280. Min Act: -0.1700
Data Index: 7769488 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7123. Min Act: -0.1700
Data Index: 2019196 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.7123. Min Act: -0.1700
Data Index: 7595986 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.6967. Min Act: -0.1700
Data Index: 3205708 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.6967. Min Act: -0.1700
Data Index: 873795 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.6967. Min Act: -0.1700
Data Index: 8637970 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.6967. Min Act: -0.1700
Data Index: 8228855 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.6810. Min Act: -0.1700
Data Index: 7991172 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9156. Min Range: -3.9156
Max Act: 3.6810. Min Act: -0.1700
Data Index: 7424001 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19