Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5491 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 171379 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 3047719 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1077. Min Act: -0.1700
Data Index: 5486085 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0452. Min Act: -0.1700
Data Index: 5569804 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0140. Min Act: -0.1700
Data Index: 4871407 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0140. Min Act: -0.1700
Data Index: 8448993 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.9515. Min Act: -0.1700
Data Index: 3701276 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.9515. Min Act: -0.1700
Data Index: 2404667 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.9202. Min Act: -0.1700
Data Index: 1532868 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8890. Min Act: -0.1700
Data Index: 7982535 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8577. Min Act: -0.1700
Data Index: 7217177 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8577. Min Act: -0.1700
Data Index: 476348 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8577. Min Act: -0.1700
Data Index: 971195 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8577. Min Act: -0.1700
Data Index: 1843886 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8577. Min Act: -0.1700
Data Index: 3425889 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8265. Min Act: -0.1700
Data Index: 3316906 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.7952. Min Act: -0.1700
Data Index: 5157683 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8265. Min Act: -0.1700
Data Index: 2939868 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8265. Min Act: -0.1700
Data Index: 4726977 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4202. Min Range: -5.4202
Max Act: 4.8265. Min Act: -0.1700
Data Index: 1351433 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19