Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.6021. Min Act: -0.1700
Data Index: 961542 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.4771. Min Act: -0.1700
Data Index: 8333414 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.4459. Min Act: -0.1700
Data Index: 1107393 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.3521. Min Act: -0.1700
Data Index: 5411189 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.3209. Min Act: -0.1700
Data Index: 4782586 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.1959. Min Act: -0.1700
Data Index: 3241714 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.1334. Min Act: -0.1700
Data Index: 7339733 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.1021. Min Act: -0.1700
Data Index: 5392422 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.1021. Min Act: -0.1700
Data Index: 4031016 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0709. Min Act: -0.1700
Data Index: 7278472 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.1021. Min Act: -0.1700
Data Index: 7670013 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0709. Min Act: -0.1700
Data Index: 6728259 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0396. Min Act: -0.1700
Data Index: 2813132 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0396. Min Act: -0.1700
Data Index: 2867360 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0396. Min Act: -0.1700
Data Index: 4735332 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0396. Min Act: -0.1700
Data Index: 3363423 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0396. Min Act: -0.1700
Data Index: 1988355 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6021. Min Range: -5.6021
Max Act: 5.0084. Min Act: -0.1700
Data Index: 4493043 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6021. Min Range: -5.6021
Max Act: 4.9771. Min Act: -0.1700
Data Index: 5704316 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6021. Min Range: -5.6021
Max Act: 4.9771. Min Act: -0.1700
Data Index: 1198986 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19