Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4337 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.5154. Min Act: -0.1700
Data Index: 7754381 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.3904. Min Act: -0.1700
Data Index: 901514 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.3592. Min Act: -0.1700
Data Index: 6140418 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.3592. Min Act: -0.1700
Data Index: 7390395 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2967. Min Act: -0.1700
Data Index: 3078929 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2967. Min Act: -0.1700
Data Index: 2869841 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2654. Min Act: -0.1700
Data Index: 1052119 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2654. Min Act: -0.1700
Data Index: 5898415 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2342. Min Act: -0.1700
Data Index: 3642180 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2654. Min Act: -0.1700
Data Index: 3252909 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2654. Min Act: -0.1700
Data Index: 7031060 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2342. Min Act: -0.1700
Data Index: 2743 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2342. Min Act: -0.1700
Data Index: 361100 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2342. Min Act: -0.1700
Data Index: 2136386 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2342. Min Act: -0.1700
Data Index: 515181 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2029. Min Act: -0.1700
Data Index: 7636404 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2342. Min Act: -0.1700
Data Index: 2357222 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2342. Min Act: -0.1700
Data Index: 1504736 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2029. Min Act: -0.1700
Data Index: 731452 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1717. Min Act: -0.1700
Data Index: 5157842 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19