Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 4742652 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 5056220 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0138. Min Act: -0.1700
Data Index: 5219358 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 5056236 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 2710867 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9826. Min Act: -0.1700
Data Index: 6366514 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0138. Min Act: -0.1700
Data Index: 3834236 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9826. Min Act: -0.1700
Data Index: 829858 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9826. Min Act: -0.1700
Data Index: 6366508 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9513. Min Act: -0.1700
Data Index: 2959185 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9513. Min Act: -0.1700
Data Index: 5056215 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9513. Min Act: -0.1700
Data Index: 6323491 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9513. Min Act: -0.1700
Data Index: 7166201 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9513. Min Act: -0.1700
Data Index: 1443531 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9513. Min Act: -0.1700
Data Index: 1589478 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9513. Min Act: -0.1700
Data Index: 5704807 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9201. Min Act: -0.1700
Data Index: 3158814 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9201. Min Act: -0.1700
Data Index: 1589495 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9201. Min Act: -0.1699
Data Index: 5011562 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9201. Min Act: -0.1700
Data Index: 2290835 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19