Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2377. Min Range: -6.2377
Max Act: 6.2377. Min Act: -0.1700
Data Index: 56650 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2377. Min Range: -6.2377
Max Act: 6.2064. Min Act: -0.1700
Data Index: 4967832 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2377. Min Range: -6.2377
Max Act: 6.1439. Min Act: -0.1700
Data Index: 8340251 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2377. Min Range: -6.2377
Max Act: 6.1127. Min Act: -0.1700
Data Index: 88953 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2377. Min Range: -6.2377
Max Act: 6.0814. Min Act: -0.1700
Data Index: 1779978 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2377. Min Range: -6.2377
Max Act: 6.0502. Min Act: -0.1700
Data Index: 5818238 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2377. Min Range: -6.2377
Max Act: 6.0189. Min Act: -0.1700
Data Index: 5153196 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.9877. Min Act: -0.1700
Data Index: 3411126 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.9252. Min Act: -0.1700
Data Index: 2993850 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8939. Min Act: -0.1700
Data Index: 5453044 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8627. Min Act: -0.1700
Data Index: 1659715 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8627. Min Act: -0.1700
Data Index: 8445106 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8627. Min Act: -0.1700
Data Index: 7668152 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8627. Min Act: -0.1700
Data Index: 7715393 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8627. Min Act: -0.1700
Data Index: 7789020 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8002. Min Act: -0.1700
Data Index: 3813624 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8314. Min Act: -0.1700
Data Index: 222389 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8314. Min Act: -0.1700
Data Index: 1779975 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8002. Min Act: -0.1700
Data Index: 7076367 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2377. Min Range: -6.2377
Max Act: 5.8002. Min Act: -0.1700
Data Index: 5690992 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19