Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.9796. Min Act: -0.1700
Data Index: 1598722 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.9456. Min Act: -0.1700
Data Index: 952396 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.9372. Min Act: -0.1700
Data Index: 4382690 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.9287. Min Act: -0.1700
Data Index: 3280189 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.9031. Min Act: -0.1700
Data Index: 6569710 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8946. Min Act: -0.1690
Data Index: 152174 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8860. Min Act: -0.1700
Data Index: 1512630 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8690. Min Act: -0.1700
Data Index: 2544037 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8775. Min Act: -0.1700
Data Index: 3308139 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8775. Min Act: -0.1700
Data Index: 6062795 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8690. Min Act: -0.1700
Data Index: 8586706 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8860. Min Act: -0.1700
Data Index: 3033379 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8690. Min Act: -0.1700
Data Index: 5745805 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8518. Min Act: -0.1700
Data Index: 6408710 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8518. Min Act: -0.1700
Data Index: 3623393 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8518. Min Act: -0.1700
Data Index: 5312712 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8518. Min Act: -0.1700
Data Index: 6464514 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8347. Min Act: -0.1700
Data Index: 756250 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8433. Min Act: -0.1700
Data Index: 6802240 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9796. Min Range: -1.9796
Max Act: 1.8347. Min Act: -0.1700
Data Index: 1972200 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19