Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8911. Min Act: -0.1700
Data Index: 178513 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8286. Min Act: -0.1700
Data Index: 4312608 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7348. Min Act: -0.1700
Data Index: 300384 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6411. Min Act: -0.1700
Data Index: 5784967 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6411. Min Act: -0.1700
Data Index: 7552938 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6411. Min Act: -0.1700
Data Index: 4983231 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6098. Min Act: -0.1700
Data Index: 2619385 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 2378441 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5473. Min Act: -0.1700
Data Index: 3504749 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5473. Min Act: -0.1700
Data Index: 5108779 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5473. Min Act: -0.1700
Data Index: 8449290 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5473. Min Act: -0.1700
Data Index: 6877265 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5473. Min Act: -0.1700
Data Index: 8437810 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.4848. Min Act: -0.1700
Data Index: 3227283 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5161. Min Act: -0.1700
Data Index: 6454313 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5161. Min Act: -0.1700
Data Index: 736337 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.4848. Min Act: -0.1700
Data Index: 3969011 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5161. Min Act: -0.1700
Data Index: 2904332 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5161. Min Act: -0.1700
Data Index: 3402165 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5161. Min Act: -0.1700
Data Index: 7468832 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19