Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1281. Min Range: -3.1281
Max Act: 3.1124. Min Act: -0.1700
Data Index: 5410621 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1281. Min Range: -3.1281
Max Act: 3.1281. Min Act: -0.1700
Data Index: 5292299 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1281. Min Range: -3.1281
Max Act: 3.0493. Min Act: -0.1700
Data Index: 849867 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1281. Min Range: -3.1281
Max Act: 3.0335. Min Act: -0.1700
Data Index: 5869171 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1281. Min Range: -3.1281
Max Act: 3.0335. Min Act: -0.1700
Data Index: 2832699 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1281. Min Range: -3.1281
Max Act: 3.0019. Min Act: -0.1700
Data Index: 3732761 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.9861. Min Act: -0.1700
Data Index: 1195683 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.9861. Min Act: -0.1700
Data Index: 2447146 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.9070. Min Act: -0.1700
Data Index: 1624321 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.9228. Min Act: -0.1700
Data Index: 3499539 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.9228. Min Act: -0.1700
Data Index: 5549048 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8911. Min Act: -0.1700
Data Index: 3486962 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8752. Min Act: -0.1700
Data Index: 4139145 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8752. Min Act: -0.1700
Data Index: 7288914 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8593. Min Act: -0.1700
Data Index: 7222009 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8593. Min Act: -0.1700
Data Index: 5549049 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8752. Min Act: -0.1700
Data Index: 4215047 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8593. Min Act: -0.1700
Data Index: 5853310 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8593. Min Act: -0.1700
Data Index: 2701760 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1281. Min Range: -3.1281
Max Act: 2.8593. Min Act: -0.1700
Data Index: 6060834 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19