Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1023 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6794. Min Act: -0.1700
Data Index: 7983146 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.7420. Min Act: -0.1700
Data Index: 5041990 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6794. Min Act: -0.1700
Data Index: 8726154 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6794. Min Act: -0.1700
Data Index: 4525685 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6481. Min Act: -0.1700
Data Index: 729645 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6481. Min Act: -0.1700
Data Index: 8349152 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6325. Min Act: -0.1700
Data Index: 2576072 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6325. Min Act: -0.1700
Data Index: 1716730 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5855. Min Act: -0.1700
Data Index: 6709811 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5855. Min Act: -0.1700
Data Index: 7316417 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5542. Min Act: -0.1700
Data Index: 2526798 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5542. Min Act: -0.1700
Data Index: 6913300 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5542. Min Act: -0.1700
Data Index: 3506560 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5542. Min Act: -0.1700
Data Index: 7549982 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5542. Min Act: -0.1700
Data Index: 2610138 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5699. Min Act: -0.1700
Data Index: 7583628 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5386. Min Act: -0.1700
Data Index: 5213607 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5073. Min Act: -0.1700
Data Index: 3385086 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5073. Min Act: -0.1700
Data Index: 783484 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5229. Min Act: -0.1700
Data Index: 5206458 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19