Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4005 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1213. Min Range: -4.1213
Max Act: 4.1213. Min Act: -0.1700
Data Index: 1066942 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1213. Min Range: -4.1213
Max Act: 4.1213. Min Act: -0.1700
Data Index: 5856472 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1213. Min Range: -4.1213
Max Act: 4.0901. Min Act: -0.1700
Data Index: 3983985 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1213. Min Range: -4.1213
Max Act: 4.0901. Min Act: -0.1700
Data Index: 8634879 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1213. Min Range: -4.1213
Max Act: 4.0588. Min Act: -0.1700
Data Index: 7610195 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9963. Min Act: -0.1700
Data Index: 5592868 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1213. Min Range: -4.1213
Max Act: 4.0275. Min Act: -0.1700
Data Index: 4529761 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9963. Min Act: -0.1700
Data Index: 5819359 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9963. Min Act: -0.1700
Data Index: 7482079 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9963. Min Act: -0.1700
Data Index: 1339961 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9963. Min Act: -0.1700
Data Index: 698361 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9650. Min Act: -0.1700
Data Index: 249417 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9338. Min Act: -0.1700
Data Index: 6155429 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9338. Min Act: -0.1700
Data Index: 8580271 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9650. Min Act: -0.1700
Data Index: 629331 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9650. Min Act: -0.1700
Data Index: 7823667 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9650. Min Act: -0.1700
Data Index: 4158904 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9338. Min Act: -0.1700
Data Index: 4422571 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9338. Min Act: -0.1700
Data Index: 5915251 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1213. Min Range: -4.1213
Max Act: 3.9025. Min Act: -0.1700
Data Index: 6255049 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19