Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.7794. Min Act: -0.1700
Data Index: 4526885 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.7169. Min Act: -0.1700
Data Index: 3284364 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.7169. Min Act: -0.1700
Data Index: 1164629 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.5919. Min Act: -0.1700
Data Index: 7263306 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.5606. Min Act: -0.1700
Data Index: 1152013 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.5606. Min Act: -0.1700
Data Index: 5716318 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.5606. Min Act: -0.1700
Data Index: 5548309 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.5294. Min Act: -0.1700
Data Index: 62514 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.5294. Min Act: -0.1700
Data Index: 5085191 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.5294. Min Act: -0.1700
Data Index: 6310217 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.4669. Min Act: -0.1700
Data Index: 5544771 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.4356. Min Act: -0.1700
Data Index: 4455235 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.4356. Min Act: -0.1700
Data Index: 272363 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.3731. Min Act: -0.1700
Data Index: 37855 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.3731. Min Act: -0.1700
Data Index: 3170398 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.3419. Min Act: -0.1700
Data Index: 1696410 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.3106. Min Act: -0.1700
Data Index: 351193 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.2794. Min Act: -0.1700
Data Index: 3387451 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.2481. Min Act: -0.1700
Data Index: 4652143 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7794. Min Range: -6.7794
Max Act: 6.2481. Min Act: -0.1700
Data Index: 2297337 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19