Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3521. Min Range: -6.3521
Max Act: 6.3521. Min Act: -0.1700
Data Index: 4682574 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3521. Min Range: -6.3521
Max Act: 6.3209. Min Act: -0.1700
Data Index: 3833956 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3521. Min Range: -6.3521
Max Act: 6.2584. Min Act: -0.1700
Data Index: 1148817 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3521. Min Range: -6.3521
Max Act: 6.1959. Min Act: -0.1700
Data Index: 2655913 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3521. Min Range: -6.3521
Max Act: 6.1021. Min Act: -0.1700
Data Index: 2095173 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3521. Min Range: -6.3521
Max Act: 6.0709. Min Act: -0.1700
Data Index: 4648902 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3521. Min Range: -6.3521
Max Act: 6.0396. Min Act: -0.1700
Data Index: 4011262 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.9771. Min Act: -0.1700
Data Index: 3605510 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.9771. Min Act: -0.1700
Data Index: 2410095 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.9771. Min Act: -0.1700
Data Index: 5010663 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.9146. Min Act: -0.1700
Data Index: 593443 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8834. Min Act: -0.1700
Data Index: 934987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8521. Min Act: -0.1700
Data Index: 6843984 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8521. Min Act: -0.1700
Data Index: 2628923 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8209. Min Act: -0.1700
Data Index: 6090978 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8521. Min Act: -0.1700
Data Index: 5268026 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8209. Min Act: -0.1700
Data Index: 5017783 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8209. Min Act: -0.1700
Data Index: 2837748 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.8209. Min Act: -0.1700
Data Index: 5668662 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3521. Min Range: -6.3521
Max Act: 5.7896. Min Act: -0.1700
Data Index: 2212266 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19