Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.7774. Min Act: -0.1700
Data Index: 346042 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 8667869 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 2782439 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.3399. Min Act: -0.1700
Data Index: 6045280 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.2462. Min Act: -0.1700
Data Index: 7909515 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.2149. Min Act: -0.1700
Data Index: 6036940 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.1524. Min Act: -0.1700
Data Index: 5314264 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.1212. Min Act: -0.1700
Data Index: 7823994 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.1524. Min Act: -0.1700
Data Index: 7390926 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7774. Min Range: -7.7774
Max Act: 7.0587. Min Act: -0.1700
Data Index: 4825595 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9962. Min Act: -0.1700
Data Index: 7381281 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9962. Min Act: -0.1700
Data Index: 5501127 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9649. Min Act: -0.1700
Data Index: 1910631 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9962. Min Act: -0.1700
Data Index: 6894473 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9649. Min Act: -0.1700
Data Index: 4381685 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9649. Min Act: -0.1700
Data Index: 3785006 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9649. Min Act: -0.1700
Data Index: 8063180 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9649. Min Act: -0.1700
Data Index: 6770946 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9337. Min Act: -0.1700
Data Index: 3359376 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7774. Min Range: -7.7774
Max Act: 6.9337. Min Act: -0.1700
Data Index: 7438272 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19