Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4012. Min Range: -9.4012
Max Act: 9.4012. Min Act: -0.1700
Data Index: 3425837 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4012. Min Range: -9.4012
Max Act: 9.2762. Min Act: -0.1700
Data Index: 1324920 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4012. Min Range: -9.4012
Max Act: 9.2762. Min Act: -0.1700
Data Index: 1915561 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4012. Min Range: -9.4012
Max Act: 9.2137. Min Act: -0.1700
Data Index: 838076 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4012. Min Range: -9.4012
Max Act: 9.2137. Min Act: -0.1700
Data Index: 7537838 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4012. Min Range: -9.4012
Max Act: 9.2762. Min Act: -0.1700
Data Index: 5444930 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4012. Min Range: -9.4012
Max Act: 9.0262. Min Act: -0.1700
Data Index: 7009922 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.9637. Min Act: -0.1700
Data Index: 3934898 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.9637. Min Act: -0.1700
Data Index: 8656338 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.9637. Min Act: -0.1700
Data Index: 1743500 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.9637. Min Act: -0.1700
Data Index: 2957685 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.8387. Min Act: -0.1700
Data Index: 434725 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.8387. Min Act: -0.1700
Data Index: 8454408 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.8387. Min Act: -0.1700
Data Index: 3299975 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.8387. Min Act: -0.1700
Data Index: 7514228 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.7762. Min Act: -0.1700
Data Index: 2485234 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.7762. Min Act: -0.1700
Data Index: 4330094 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.7762. Min Act: -0.1700
Data Index: 5228556 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.7137. Min Act: -0.1700
Data Index: 3287549 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4012. Min Range: -9.4012
Max Act: 8.6512. Min Act: -0.1700
Data Index: 4673246 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19