Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 618 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9544. Min Act: -0.1700
Data Index: 8783406 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9857. Min Act: -0.1700
Data Index: 6605071 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9232. Min Act: -0.1700
Data Index: 7360388 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4789316 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9544. Min Act: -0.1700
Data Index: 6971134 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9232. Min Act: -0.1700
Data Index: 7544596 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9232. Min Act: -0.1700
Data Index: 3258117 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8919. Min Act: -0.1700
Data Index: 3324695 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9544. Min Act: -0.1700
Data Index: 8477953 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8919. Min Act: -0.1700
Data Index: 1869522 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8919. Min Act: -0.1700
Data Index: 1578601 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4920597 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8294. Min Act: -0.1700
Data Index: 551059 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8607. Min Act: -0.1700
Data Index: 5636504 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8607. Min Act: -0.1700
Data Index: 5529872 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8294. Min Act: -0.1700
Data Index: 3070698 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8294. Min Act: -0.1700
Data Index: 6762216 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8294. Min Act: -0.1700
Data Index: 2405971 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.7982. Min Act: -0.1700
Data Index: 1027346 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8607. Min Act: -0.1700
Data Index: 7471178 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19