Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1676 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.6356. Min Act: -0.1700
Data Index: 1057818 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.5106. Min Act: -0.1700
Data Index: 1140006 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.4481. Min Act: -0.1700
Data Index: 8178933 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.3856. Min Act: -0.1700
Data Index: 4125816 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.3231. Min Act: -0.1700
Data Index: 5606480 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2919. Min Act: -0.1700
Data Index: 1522299 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2919. Min Act: -0.1700
Data Index: 5634182 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2606. Min Act: -0.1700
Data Index: 679415 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2606. Min Act: -0.1700
Data Index: 3210883 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2606. Min Act: -0.1700
Data Index: 963133 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2294. Min Act: -0.1700
Data Index: 338297 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2606. Min Act: -0.1700
Data Index: 279142 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2294. Min Act: -0.1700
Data Index: 71060 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.2294. Min Act: -0.1700
Data Index: 2478217 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.1981. Min Act: -0.1700
Data Index: 2530723 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.1981. Min Act: -0.1700
Data Index: 8762428 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.1981. Min Act: -0.1700
Data Index: 1285842 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.1981. Min Act: -0.1700
Data Index: 5289628 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.1669. Min Act: -0.1700
Data Index: 5588655 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6356. Min Range: -4.6356
Max Act: 4.1669. Min Act: -0.1700
Data Index: 5392167 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19