Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2524 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.4222. Min Act: -0.1700
Data Index: 5961574 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.4222. Min Act: -0.1700
Data Index: 8803678 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.3597. Min Act: -0.1700
Data Index: 4754393 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.3285. Min Act: -0.1700
Data Index: 4754392 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6621181 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.3285. Min Act: -0.1700
Data Index: 5478835 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6060991 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.3285. Min Act: -0.1700
Data Index: 7622018 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2972. Min Act: -0.1700
Data Index: 5633215 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.3285. Min Act: -0.1700
Data Index: 508684 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2660. Min Act: -0.1700
Data Index: 2354176 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2660. Min Act: -0.1700
Data Index: 6016362 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2660. Min Act: -0.1700
Data Index: 4901720 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2660. Min Act: -0.1700
Data Index: 2493777 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2660. Min Act: -0.1700
Data Index: 5860933 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2347. Min Act: -0.1700
Data Index: 7218400 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1722. Min Act: -0.1700
Data Index: 6368049 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1722. Min Act: -0.1700
Data Index: 509285 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.2035. Min Act: -0.1700
Data Index: 6635650 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4222. Min Range: -5.4222
Max Act: 5.1722. Min Act: -0.1700
Data Index: 3190786 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19