Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3705 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.7693. Min Act: -0.1700
Data Index: 2771307 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.7381. Min Act: -0.1700
Data Index: 1015420 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6656358 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.5818. Min Act: -0.1700
Data Index: 1596053 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.6131. Min Act: -0.1700
Data Index: 5095735 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.5506. Min Act: -0.1700
Data Index: 6802532 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.5193. Min Act: -0.1700
Data Index: 7791424 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.5506. Min Act: -0.1700
Data Index: 7020568 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.5193. Min Act: -0.1700
Data Index: 4497935 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.5506. Min Act: -0.1700
Data Index: 5886143 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4881. Min Act: -0.1700
Data Index: 5173381 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4881. Min Act: -0.1700
Data Index: 4688052 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4881. Min Act: -0.1700
Data Index: 6740310 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4881. Min Act: -0.1700
Data Index: 886297 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4568. Min Act: -0.1700
Data Index: 322557 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4881. Min Act: -0.1700
Data Index: 8690765 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4568. Min Act: -0.1700
Data Index: 1773955 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4568. Min Act: -0.1700
Data Index: 1148402 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4568. Min Act: -0.1700
Data Index: 1930826 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7693. Min Range: -4.7693
Max Act: 4.4256. Min Act: -0.1700
Data Index: 2780246 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19