Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6361 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.2651. Min Act: -0.1700
Data Index: 8297779 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.2026. Min Act: -0.1700
Data Index: 2660606 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.2339. Min Act: -0.1700
Data Index: 2635887 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.2339. Min Act: -0.1700
Data Index: 8255616 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.2339. Min Act: -0.1700
Data Index: 5639763 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.2339. Min Act: -0.1700
Data Index: 8767068 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1714. Min Act: -0.1700
Data Index: 8767067 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1401. Min Act: -0.1700
Data Index: 2065494 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1401. Min Act: -0.1700
Data Index: 1969978 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1401. Min Act: -0.1700
Data Index: 7033537 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1089. Min Act: -0.1700
Data Index: 1869672 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1089. Min Act: -0.1700
Data Index: 7209641 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1089. Min Act: -0.1700
Data Index: 1117112 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.1089. Min Act: -0.1700
Data Index: 4630964 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.0776. Min Act: -0.1700
Data Index: 7573484 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.0776. Min Act: -0.1700
Data Index: 676048 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.0776. Min Act: -0.1700
Data Index: 5648853 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.0776. Min Act: -0.1700
Data Index: 403430 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.0464. Min Act: -0.1700
Data Index: 7059492 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2651. Min Range: -6.2651
Max Act: 6.0464. Min Act: -0.1700
Data Index: 7237883 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19