Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4431 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1737. Min Range: -5.1737
Max Act: 5.1737. Min Act: -0.1700
Data Index: 4956204 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1737. Min Range: -5.1737
Max Act: 5.1112. Min Act: -0.1700
Data Index: 7410310 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1737. Min Range: -5.1737
Max Act: 5.0487. Min Act: -0.1700
Data Index: 5099663 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1737. Min Range: -5.1737
Max Act: 5.0487. Min Act: -0.1700
Data Index: 3748186 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1737. Min Range: -5.1737
Max Act: 5.0487. Min Act: -0.1700
Data Index: 413567 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 8219886 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9862. Min Act: -0.1700
Data Index: 1972290 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9862. Min Act: -0.1700
Data Index: 4005157 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 3070354 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 2319395 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5439099 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 3723924 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 7588276 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5905770 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9237. Min Act: -0.1700
Data Index: 5126986 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 6641372 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9550. Min Act: -0.1700
Data Index: 837141 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9237. Min Act: -0.1700
Data Index: 2535108 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.9237. Min Act: -0.1700
Data Index: 6452222 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1737. Min Range: -5.1737
Max Act: 4.8925. Min Act: -0.1700
Data Index: 4005158 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19