Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5833 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.7553. Min Act: -0.1700
Data Index: 7185179 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.7241. Min Act: -0.1700
Data Index: 2017518 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.6928. Min Act: -0.1700
Data Index: 4991589 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.6303. Min Act: -0.1700
Data Index: 2703489 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.5991. Min Act: -0.1700
Data Index: 8479277 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.5991. Min Act: -0.1700
Data Index: 2081876 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.5678. Min Act: -0.1700
Data Index: 5565142 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.5366. Min Act: -0.1700
Data Index: 1990601 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.4428. Min Act: -0.1700
Data Index: 7169076 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.4741. Min Act: -0.1700
Data Index: 3007603 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4403746 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.4116. Min Act: -0.1700
Data Index: 5862691 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.4428. Min Act: -0.1700
Data Index: 6261981 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.3803. Min Act: -0.1700
Data Index: 1288277 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.4116. Min Act: -0.1700
Data Index: 1643730 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.4116. Min Act: -0.1700
Data Index: 122024 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.3491. Min Act: -0.1700
Data Index: 4852632 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.3803. Min Act: -0.1700
Data Index: 3494144 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.3178. Min Act: -0.1700
Data Index: 3240452 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7553. Min Range: -6.7553
Max Act: 6.3491. Min Act: -0.1700
Data Index: 4974536 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19