Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.9468. Min Act: -0.1700
Data Index: 5227184 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.9128. Min Act: -0.1700
Data Index: 6989676 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8701. Min Act: -0.1700
Data Index: 837037 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8872. Min Act: -0.1700
Data Index: 7477096 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8615. Min Act: -0.1700
Data Index: 8755254 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8615. Min Act: -0.1700
Data Index: 1623510 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8530. Min Act: -0.1700
Data Index: 6509804 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8615. Min Act: -0.1700
Data Index: 2626548 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8444. Min Act: -0.1700
Data Index: 7649704 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8359. Min Act: -0.1700
Data Index: 2781205 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8444. Min Act: -0.1700
Data Index: 6334744 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8273. Min Act: -0.1700
Data Index: 283143 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8273. Min Act: -0.1700
Data Index: 1779269 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8273. Min Act: -0.1700
Data Index: 4968386 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8187. Min Act: -0.1700
Data Index: 1137598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8187. Min Act: -0.1700
Data Index: 1399804 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8187. Min Act: -0.1700
Data Index: 309765 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8015. Min Act: -0.1700
Data Index: 6817014 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8187. Min Act: -0.1700
Data Index: 3135523 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9468. Min Range: -1.9468
Max Act: 1.8101. Min Act: -0.1700
Data Index: 4878697 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19