Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0657. Min Range: -3.0657
Max Act: 3.0657. Min Act: -0.1700
Data Index: 4188415 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9867. Min Act: -0.1700
Data Index: 2609430 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0657. Min Range: -3.0657
Max Act: 3.0025. Min Act: -0.1700
Data Index: 1384880 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0657. Min Range: -3.0657
Max Act: 3.0657. Min Act: -0.1700
Data Index: 228322 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0657. Min Range: -3.0657
Max Act: 3.0025. Min Act: -0.1700
Data Index: 3970551 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9551. Min Act: -0.1700
Data Index: 7852324 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9709. Min Act: -0.1700
Data Index: 1476124 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9709. Min Act: -0.1700
Data Index: 1276169 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9392. Min Act: -0.1700
Data Index: 2141119 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9076. Min Act: -0.1700
Data Index: 2821776 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9551. Min Act: -0.1700
Data Index: 4520412 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9234. Min Act: -0.1700
Data Index: 5577163 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9076. Min Act: -0.1700
Data Index: 5964158 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9076. Min Act: -0.1700
Data Index: 6878116 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9234. Min Act: -0.1700
Data Index: 1965194 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9076. Min Act: -0.1700
Data Index: 3842218 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.8917. Min Act: -0.1700
Data Index: 490259 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9076. Min Act: -0.1700
Data Index: 3014465 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9076. Min Act: -0.1700
Data Index: 2239784 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0657. Min Range: -3.0657
Max Act: 2.9234. Min Act: -0.1700
Data Index: 214594 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19