Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0301. Min Range: -7.0301
Max Act: 7.0301. Min Act: -0.1700
Data Index: 7003357 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.8738. Min Act: -0.1700
Data Index: 974105 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.8113. Min Act: -0.1700
Data Index: 7193890 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.7488. Min Act: -0.1700
Data Index: 7684444 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.6863. Min Act: -0.1700
Data Index: 7014258 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.7176. Min Act: -0.1700
Data Index: 6786640 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.6551. Min Act: -0.1700
Data Index: 3923846 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.6863. Min Act: -0.1700
Data Index: 875621 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.6551. Min Act: -0.1700
Data Index: 1653507 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.6238. Min Act: -0.1700
Data Index: 7893893 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.5613. Min Act: -0.1700
Data Index: 8489005 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.5613. Min Act: -0.1700
Data Index: 770549 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.6238. Min Act: -0.1700
Data Index: 8562768 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.5301. Min Act: -0.1700
Data Index: 1234271 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.5613. Min Act: -0.1700
Data Index: 1698302 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.5613. Min Act: -0.1700
Data Index: 5687982 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.4988. Min Act: -0.1700
Data Index: 6533063 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.4988. Min Act: -0.1700
Data Index: 4028864 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.5926. Min Act: -0.1700
Data Index: 2566694 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0301. Min Range: -7.0301
Max Act: 6.4676. Min Act: -0.1700
Data Index: 1698303 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19