Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2126 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.9875. Min Act: -0.1700
Data Index: 5982247 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.6125. Min Act: -0.1700
Data Index: 181201 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.6125. Min Act: -0.1700
Data Index: 8364720 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5812. Min Act: -0.1700
Data Index: 6884707 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5500. Min Act: -0.1700
Data Index: 2918717 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3844523 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4562. Min Act: -0.1700
Data Index: 828535 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4250. Min Act: -0.1700
Data Index: 7046322 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4562. Min Act: -0.1700
Data Index: 2332595 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4875. Min Act: -0.1700
Data Index: 6527395 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4562. Min Act: -0.1700
Data Index: 921149 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4250. Min Act: -0.1700
Data Index: 462951 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4250. Min Act: -0.1700
Data Index: 5862052 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4250. Min Act: -0.1700
Data Index: 8506284 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3937. Min Act: -0.1700
Data Index: 3578842 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4250. Min Act: -0.1700
Data Index: 5140108 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3625. Min Act: -0.1700
Data Index: 7843290 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3625. Min Act: -0.1700
Data Index: 3530568 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3625. Min Act: -0.1700
Data Index: 4304987 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3312. Min Act: -0.1700
Data Index: 6354668 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19