Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.1882. Min Act: -0.1700
Data Index: 7768266 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0944. Min Act: -0.1700
Data Index: 794715 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0944. Min Act: -0.1700
Data Index: 2729625 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0632. Min Act: -0.1700
Data Index: 5907339 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0319. Min Act: -0.1700
Data Index: 1222498 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0007. Min Act: -0.1700
Data Index: 5784594 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4666883 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9694. Min Act: -0.1700
Data Index: 7780452 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 5936002 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 4608698 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 4311161 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9069. Min Act: -0.1700
Data Index: 4714803 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 4989849 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 4612101 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 8159911 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9069. Min Act: -0.1700
Data Index: 3828160 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8444. Min Act: -0.1700
Data Index: 6432545 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8444. Min Act: -0.1700
Data Index: 4944858 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8444. Min Act: -0.1700
Data Index: 6506162 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8444. Min Act: -0.1700
Data Index: 6776225 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19