Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.9196. Min Act: -0.1700
Data Index: 2280297 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.8257. Min Act: -0.1700
Data Index: 8036335 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.7945. Min Act: -0.1700
Data Index: 4059737 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.6537. Min Act: -0.1700
Data Index: 997952 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.6224. Min Act: -0.1700
Data Index: 514605 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.6068. Min Act: -0.1700
Data Index: 6317617 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5754. Min Act: -0.1700
Data Index: 3445688 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5598. Min Act: -0.1700
Data Index: 7977189 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5911. Min Act: -0.1700
Data Index: 4788888 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5598. Min Act: -0.1700
Data Index: 5134853 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5441. Min Act: -0.1700
Data Index: 6813080 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.4972. Min Act: -0.1700
Data Index: 5275426 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5285. Min Act: -0.1700
Data Index: 3744284 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5285. Min Act: -0.1700
Data Index: 1725266 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5285. Min Act: -0.1700
Data Index: 6702965 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.5128. Min Act: -0.1700
Data Index: 7206616 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.4658. Min Act: -0.1700
Data Index: 5898231 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.4815. Min Act: -0.1700
Data Index: 2895889 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.4972. Min Act: -0.1700
Data Index: 1024096 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9196. Min Range: -3.9196
Max Act: 3.4502. Min Act: -0.1700
Data Index: 5214412 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19