Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 562 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3121. Min Range: -6.3121
Max Act: 6.3121. Min Act: -0.1700
Data Index: 8511681 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.9684. Min Act: -0.1700
Data Index: 8773652 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.9996. Min Act: -0.1700
Data Index: 7031571 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.9059. Min Act: -0.1700
Data Index: 8539876 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8746. Min Act: -0.1700
Data Index: 6893225 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8434. Min Act: -0.1700
Data Index: 2816308 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8746. Min Act: -0.1700
Data Index: 30440 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8746. Min Act: -0.1700
Data Index: 6619039 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8746. Min Act: -0.1700
Data Index: 1570254 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8746. Min Act: -0.1700
Data Index: 7026305 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5452833 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 3533065 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1256230 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 4725536 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 3976317 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 6900679 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 2907187 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1526867 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.7496. Min Act: -0.1700
Data Index: 8121739 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3121. Min Range: -6.3121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 3628050 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19