Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.9981. Min Act: -0.1700
Data Index: 8021928 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.9044. Min Act: -0.1700
Data Index: 6782602 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.8731. Min Act: -0.1700
Data Index: 609414 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.7481. Min Act: -0.1700
Data Index: 289604 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.6856. Min Act: -0.1700
Data Index: 2111380 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.7169. Min Act: -0.1700
Data Index: 6415564 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.6544. Min Act: -0.1700
Data Index: 8587629 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.6231. Min Act: -0.1700
Data Index: 1167607 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5919. Min Act: -0.1700
Data Index: 6512125 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5606. Min Act: -0.1700
Data Index: 1894949 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5919. Min Act: -0.1700
Data Index: 4098220 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5294. Min Act: -0.1700
Data Index: 7471710 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5606. Min Act: -0.1700
Data Index: 5944241 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5606. Min Act: -0.1700
Data Index: 8782750 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5606. Min Act: -0.1700
Data Index: 5100105 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5606. Min Act: -0.1700
Data Index: 1867629 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5294. Min Act: -0.1700
Data Index: 1527051 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5294. Min Act: -0.1700
Data Index: 3534430 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5294. Min Act: -0.1700
Data Index: 8571082 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9981. Min Range: -4.9981
Max Act: 4.5294. Min Act: -0.1700
Data Index: 7386358 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19