Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.6578. Min Act: -0.1700
Data Index: 8199240 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.6578. Min Act: -0.1700
Data Index: 2146328 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5328. Min Act: -0.1700
Data Index: 2636349 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5016. Min Act: -0.1700
Data Index: 7368808 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4703. Min Act: -0.1700
Data Index: 5848340 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.5016. Min Act: -0.1700
Data Index: 8638697 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4703. Min Act: -0.1700
Data Index: 8044584 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4391. Min Act: -0.1700
Data Index: 7084932 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 5677313 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4078. Min Act: -0.1700
Data Index: 4666170 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.4078. Min Act: -0.1700
Data Index: 5898211 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 6988429 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 1469039 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3766. Min Act: -0.1700
Data Index: 2986131 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3453. Min Act: -0.1700
Data Index: 2588886 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.3141. Min Act: -0.1700
Data Index: 4095451 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2828. Min Act: -0.1700
Data Index: 8282830 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2828. Min Act: -0.1700
Data Index: 8612951 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2516. Min Act: -0.1700
Data Index: 4953291 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6578. Min Range: -6.6578
Max Act: 6.2516. Min Act: -0.1700
Data Index: 860028 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19