Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0296. Min Range: -3.0296
Max Act: 3.0296. Min Act: -0.1700
Data Index: 4843688 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9822. Min Act: -0.1700
Data Index: 1409419 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9506. Min Act: -0.1700
Data Index: 6715152 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9506. Min Act: -0.1700
Data Index: 53661 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9189. Min Act: -0.1700
Data Index: 4339225 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9664. Min Act: -0.1700
Data Index: 1409417 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9664. Min Act: -0.1700
Data Index: 481431 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9506. Min Act: -0.1700
Data Index: 2941419 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9506. Min Act: -0.1700
Data Index: 7904085 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9189. Min Act: -0.1700
Data Index: 1181988 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9347. Min Act: -0.1700
Data Index: 7530902 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9189. Min Act: -0.1700
Data Index: 7140156 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9347. Min Act: -0.1700
Data Index: 811082 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9189. Min Act: -0.1700
Data Index: 7418302 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9189. Min Act: -0.1700
Data Index: 5579225 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.9031. Min Act: -0.1700
Data Index: 1845613 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.8713. Min Act: -0.1700
Data Index: 7795426 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.8872. Min Act: -0.1700
Data Index: 1409418 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.8872. Min Act: -0.1700
Data Index: 3461919 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0296. Min Range: -3.0296
Max Act: 2.8713. Min Act: -0.1700
Data Index: 53676 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19