Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1764. Min Range: -5.1764
Max Act: 5.1764. Min Act: -0.1700
Data Index: 297940 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1764. Min Range: -5.1764
Max Act: 5.0826. Min Act: -0.1700
Data Index: 7057879 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1764. Min Range: -5.1764
Max Act: 5.0201. Min Act: -0.1700
Data Index: 3594257 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1764. Min Range: -5.1764
Max Act: 5.0201. Min Act: -0.1700
Data Index: 2432494 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.9264. Min Act: -0.1700
Data Index: 7074493 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.9264. Min Act: -0.1700
Data Index: 867653 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.9264. Min Act: -0.1700
Data Index: 7323388 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.9264. Min Act: -0.1700
Data Index: 366107 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.8951. Min Act: -0.1700
Data Index: 5004832 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.8326. Min Act: -0.1700
Data Index: 1290725 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.8014. Min Act: -0.1700
Data Index: 7364194 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.7701. Min Act: -0.1700
Data Index: 5626615 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.8014. Min Act: -0.1700
Data Index: 6650442 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.7701. Min Act: -0.1700
Data Index: 3208285 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.7389. Min Act: -0.1700
Data Index: 7811375 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.7701. Min Act: -0.1700
Data Index: 7669667 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.7701. Min Act: -0.1700
Data Index: 7417197 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.7701. Min Act: -0.1700
Data Index: 7238618 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.7701. Min Act: -0.1700
Data Index: 904133 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1764. Min Range: -5.1764
Max Act: 4.8014. Min Act: -0.1700
Data Index: 6461304 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19