Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2745. Min Range: -3.2745
Max Act: 3.2745. Min Act: -0.1700
Data Index: 7237392 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2745. Min Range: -3.2745
Max Act: 3.1645. Min Act: -0.1700
Data Index: 4437047 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2745. Min Range: -3.2745
Max Act: 3.1487. Min Act: -0.1700
Data Index: 4803364 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2745. Min Range: -3.2745
Max Act: 3.1172. Min Act: -0.1700
Data Index: 273587 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2745. Min Range: -3.2745
Max Act: 3.0700. Min Act: -0.1700
Data Index: 3536522 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2745. Min Range: -3.2745
Max Act: 3.0542. Min Act: -0.1700
Data Index: 6519164 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2745. Min Range: -3.2745
Max Act: 3.0068. Min Act: -0.1700
Data Index: 526295 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9910. Min Act: -0.1700
Data Index: 4787743 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9910. Min Act: -0.1700
Data Index: 3927965 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9752. Min Act: -0.1700
Data Index: 4576016 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9752. Min Act: -0.1700
Data Index: 3388234 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9594. Min Act: -0.1700
Data Index: 6643950 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9435. Min Act: -0.1700
Data Index: 7945754 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9435. Min Act: -0.1700
Data Index: 2740661 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9435. Min Act: -0.1700
Data Index: 3154180 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9435. Min Act: -0.1700
Data Index: 4940740 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9435. Min Act: -0.1700
Data Index: 7580662 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9119. Min Act: -0.1700
Data Index: 5600650 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9277. Min Act: -0.1700
Data Index: 4840818 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2745. Min Range: -3.2745
Max Act: 2.9277. Min Act: -0.1700
Data Index: 8671892 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19