Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.9507. Min Act: -0.1700
Data Index: 141460 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.9195. Min Act: -0.1700
Data Index: 2750501 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8882. Min Act: -0.1700
Data Index: 7782372 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8726. Min Act: -0.1700
Data Index: 7773814 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8569. Min Act: -0.1700
Data Index: 7273312 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8569. Min Act: -0.1700
Data Index: 30944 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8413. Min Act: -0.1700
Data Index: 1060564 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8257. Min Act: -0.1700
Data Index: 1919335 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8257. Min Act: -0.1700
Data Index: 4633849 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.8100. Min Act: -0.1700
Data Index: 846323 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7787. Min Act: -0.1700
Data Index: 298512 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7631. Min Act: -0.1700
Data Index: 1969203 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7631. Min Act: -0.1700
Data Index: 7630331 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7631. Min Act: -0.1700
Data Index: 3647303 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7631. Min Act: -0.1700
Data Index: 6858733 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7475. Min Act: -0.1700
Data Index: 2216639 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7475. Min Act: -0.1700
Data Index: 5223715 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7475. Min Act: -0.1700
Data Index: 7412122 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7318. Min Act: -0.1700
Data Index: 1685871 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9507. Min Range: -3.9507
Max Act: 3.7475. Min Act: -0.1700
Data Index: 2869272 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19