Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.9556. Min Act: -0.1700
Data Index: 8685469 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.9868. Min Act: -0.1700
Data Index: 7640555 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8930. Min Act: -0.1700
Data Index: 4632199 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8930. Min Act: -0.1700
Data Index: 2857737 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8930. Min Act: -0.1700
Data Index: 981687 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8305. Min Act: -0.1700
Data Index: 177180 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7992. Min Act: -0.1700
Data Index: 7526529 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8305. Min Act: -0.1700
Data Index: 8241520 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7992. Min Act: -0.1700
Data Index: 4861859 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8305. Min Act: -0.1700
Data Index: 4891151 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8305. Min Act: -0.1700
Data Index: 3305588 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.8305. Min Act: -0.1700
Data Index: 3672293 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7679. Min Act: -0.1700
Data Index: 8026327 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7679. Min Act: -0.1700
Data Index: 2810903 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7679. Min Act: -0.1700
Data Index: 6794044 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7679. Min Act: -0.1700
Data Index: 7822704 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7367. Min Act: -0.1700
Data Index: 3018096 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7367. Min Act: -0.1700
Data Index: 1132579 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7367. Min Act: -0.1700
Data Index: 2050205 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9868. Min Range: -3.9868
Max Act: 3.7367. Min Act: -0.1700
Data Index: 6950072 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19