Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5703. Min Act: -0.1700
Data Index: 1555148 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5703. Min Act: -0.1700
Data Index: 2735325 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5391. Min Act: -0.1700
Data Index: 2982833 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.5078. Min Act: -0.1700
Data Index: 3372520 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4766. Min Act: -0.1700
Data Index: 8211237 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4766. Min Act: -0.1700
Data Index: 850768 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 5238004 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 5451051 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 4955761 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 637067 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 2735323 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3516. Min Act: -0.1700
Data Index: 5500427 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3828. Min Act: -0.1700
Data Index: 6141190 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3828. Min Act: -0.1700
Data Index: 2332872 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3828. Min Act: -0.1700
Data Index: 4806189 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3828. Min Act: -0.1700
Data Index: 104682 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3828. Min Act: -0.1700
Data Index: 6612961 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3828. Min Act: -0.1700
Data Index: 7330123 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.3516. Min Act: -0.1700
Data Index: 108272 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5703. Min Range: -4.5703
Max Act: 4.4141. Min Act: -0.1700
Data Index: 4571386 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19