Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4798 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1396. Min Range: -5.1396
Max Act: 5.1396. Min Act: -0.1700
Data Index: 665457 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1396. Min Range: -5.1396
Max Act: 5.1084. Min Act: -0.1700
Data Index: 3978074 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1396. Min Range: -5.1396
Max Act: 5.0459. Min Act: -0.1700
Data Index: 5249620 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1396. Min Range: -5.1396
Max Act: 5.0771. Min Act: -0.1700
Data Index: 2941425 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1396. Min Range: -5.1396
Max Act: 5.0459. Min Act: -0.1700
Data Index: 4224078 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.9834. Min Act: -0.1700
Data Index: 7842609 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.9834. Min Act: -0.1700
Data Index: 2904111 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.9834. Min Act: -0.1700
Data Index: 7335964 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.9521. Min Act: -0.1700
Data Index: 5303357 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.9521. Min Act: -0.1700
Data Index: 947265 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.9521. Min Act: -0.1700
Data Index: 2768373 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.9209. Min Act: -0.1700
Data Index: 6171284 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8896. Min Act: -0.1700
Data Index: 2875410 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8896. Min Act: -0.1700
Data Index: 1276425 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8896. Min Act: -0.1700
Data Index: 2123194 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8896. Min Act: -0.1700
Data Index: 3306607 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8584. Min Act: -0.1700
Data Index: 314242 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8271. Min Act: -0.1700
Data Index: 4727260 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8584. Min Act: -0.1700
Data Index: 5473832 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1396. Min Range: -5.1396
Max Act: 4.8584. Min Act: -0.1700
Data Index: 3778909 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19