Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 310 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.9368. Min Act: -0.1700
Data Index: 8409157 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.9368. Min Act: -0.1700
Data Index: 6250589 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.9368. Min Act: -0.1700
Data Index: 1927136 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.9368. Min Act: -0.1700
Data Index: 3498689 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.9368. Min Act: -0.1700
Data Index: 4890968 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.9368. Min Act: -0.1700
Data Index: 8556013 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8743. Min Act: -0.1700
Data Index: 1176740 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8743. Min Act: -0.1700
Data Index: 1750953 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8743. Min Act: -0.1700
Data Index: 7915794 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8743. Min Act: -0.1700
Data Index: 441791 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8743. Min Act: -0.1700
Data Index: 2767596 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8431. Min Act: -0.1700
Data Index: 1509323 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8431. Min Act: -0.1700
Data Index: 6990143 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8431. Min Act: -0.1700
Data Index: 1759125 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.7806. Min Act: -0.1700
Data Index: 6023012 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8431. Min Act: -0.1700
Data Index: 111828 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.7806. Min Act: -0.1700
Data Index: 8161144 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8118. Min Act: -0.1700
Data Index: 4676457 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.8118. Min Act: -0.1700
Data Index: 5915611 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9368. Min Range: -4.9368
Max Act: 4.7806. Min Act: -0.1700
Data Index: 6174251 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19