Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.9717. Min Act: -0.1700
Data Index: 4105313 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.8780. Min Act: -0.1700
Data Index: 1966814 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.8155. Min Act: -0.1700
Data Index: 2330000 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.7842. Min Act: -0.1700
Data Index: 6358129 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.7217. Min Act: -0.1700
Data Index: 3615084 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.7217. Min Act: -0.1700
Data Index: 1499259 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.7217. Min Act: -0.1700
Data Index: 3773767 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.6280. Min Act: -0.1700
Data Index: 6985949 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.6905. Min Act: -0.1700
Data Index: 6153475 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.6905. Min Act: -0.1700
Data Index: 841676 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.6280. Min Act: -0.1700
Data Index: 1952262 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.6592. Min Act: -0.1700
Data Index: 4394798 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.6592. Min Act: -0.1700
Data Index: 4423880 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.6280. Min Act: -0.1700
Data Index: 6947596 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.5655. Min Act: -0.1700
Data Index: 4277108 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.5342. Min Act: -0.1700
Data Index: 6369099 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.5342. Min Act: -0.1700
Data Index: 8831109 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.5342. Min Act: -0.1700
Data Index: 3525085 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.5342. Min Act: -0.1700
Data Index: 6934405 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9717. Min Range: -4.9717
Max Act: 4.4717. Min Act: -0.1700
Data Index: 7859925 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19