Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.3959. Min Act: -0.1700
Data Index: 8224403 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.3021. Min Act: -0.1700
Data Index: 8808039 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.3021. Min Act: -0.1700
Data Index: 296394 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.2396. Min Act: -0.1700
Data Index: 8734874 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.2084. Min Act: -0.1700
Data Index: 8691689 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.1771. Min Act: -0.1700
Data Index: 6270635 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.1771. Min Act: -0.1700
Data Index: 5312213 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.1771. Min Act: -0.1700
Data Index: 1559036 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.1771. Min Act: -0.1700
Data Index: 807120 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.1459. Min Act: -0.1700
Data Index: 7523416 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.1146. Min Act: -0.1700
Data Index: 4439066 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.1146. Min Act: -0.1700
Data Index: 4382739 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.0834. Min Act: -0.1700
Data Index: 7560309 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.0834. Min Act: -0.1700
Data Index: 7356403 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.0834. Min Act: -0.1700
Data Index: 6170512 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.0521. Min Act: -0.1700
Data Index: 6618729 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3959. Min Range: -5.3959
Max Act: 4.9896. Min Act: -0.1700
Data Index: 3363929 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.0209. Min Act: -0.1700
Data Index: 736898 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.0209. Min Act: -0.1700
Data Index: 3628724 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3959. Min Range: -5.3959
Max Act: 5.0209. Min Act: -0.1700
Data Index: 1595009 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19