Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.3416. Min Act: -0.1700
Data Index: 8158837 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.2479. Min Act: -0.1700
Data Index: 4896141 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.2166. Min Act: -0.1700
Data Index: 6908196 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.1229. Min Act: -0.1700
Data Index: 1409672 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.1541. Min Act: -0.1700
Data Index: 7263712 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.1229. Min Act: -0.1700
Data Index: 6124785 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.1229. Min Act: -0.1700
Data Index: 6366400 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.1229. Min Act: -0.1700
Data Index: 4392699 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0916. Min Act: -0.1700
Data Index: 5360066 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0916. Min Act: -0.1700
Data Index: 847484 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0916. Min Act: -0.1700
Data Index: 1981077 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0916. Min Act: -0.1700
Data Index: 7977232 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0916. Min Act: -0.1700
Data Index: 3688632 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0916. Min Act: -0.1700
Data Index: 494019 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0916. Min Act: -0.1700
Data Index: 1409778 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0604. Min Act: -0.1700
Data Index: 4191376 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0604. Min Act: -0.1699
Data Index: 6367429 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0604. Min Act: -0.1700
Data Index: 901212 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0604. Min Act: -0.1700
Data Index: 755643 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3416. Min Range: -5.3416
Max Act: 5.0604. Min Act: -0.1700
Data Index: 6673225 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19