Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4923 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.9356. Min Act: -0.1700
Data Index: 3392879 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.6856. Min Act: -0.1700
Data Index: 2159813 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.6856. Min Act: -0.1700
Data Index: 3881753 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.5606. Min Act: -0.1700
Data Index: 1840593 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.5293. Min Act: -0.1700
Data Index: 8287986 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.5293. Min Act: -0.1700
Data Index: 3389890 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.5293. Min Act: -0.1700
Data Index: 3228350 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.4981. Min Act: -0.1700
Data Index: 5080047 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.4981. Min Act: -0.1700
Data Index: 2209884 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.4981. Min Act: -0.1700
Data Index: 4774620 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.4356. Min Act: -0.1700
Data Index: 8101927 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.4043. Min Act: -0.1700
Data Index: 1759085 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.3731. Min Act: -0.1700
Data Index: 7075541 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.3731. Min Act: -0.1700
Data Index: 2803635 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.3418. Min Act: -0.1700
Data Index: 7227571 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.3106. Min Act: -0.1700
Data Index: 6678536 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.3106. Min Act: -0.1700
Data Index: 2855141 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.3106. Min Act: -0.1700
Data Index: 8005460 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.2793. Min Act: -0.1700
Data Index: 3964604 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9356. Min Range: -7.9356
Max Act: 7.3106. Min Act: -0.1700
Data Index: 4692841 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19