Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.5641. Min Act: -0.1700
Data Index: 5361174 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.5016. Min Act: -0.1700
Data Index: 6536852 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.3766. Min Act: -0.1700
Data Index: 5966894 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.2516. Min Act: -0.1700
Data Index: 8433619 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.2516. Min Act: -0.1700
Data Index: 7585597 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.2516. Min Act: -0.1700
Data Index: 418618 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.2516. Min Act: -0.1700
Data Index: 3357127 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.1891. Min Act: -0.1700
Data Index: 5361173 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.1891. Min Act: -0.1700
Data Index: 7071458 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.1891. Min Act: -0.1700
Data Index: 3547274 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.0016. Min Act: -0.1700
Data Index: 6463064 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5641. Min Range: -9.5641
Max Act: 9.0641. Min Act: -0.1700
Data Index: 334233 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.9391. Min Act: -0.1700
Data Index: 4990007 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.9391. Min Act: -0.1700
Data Index: 1500978 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.8141. Min Act: -0.1700
Data Index: 4787011 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.7516. Min Act: -0.1700
Data Index: 8493518 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.7516. Min Act: -0.1700
Data Index: 2336469 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.7516. Min Act: -0.1700
Data Index: 15207 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.7516. Min Act: -0.1700
Data Index: 2689553 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5641. Min Range: -9.5641
Max Act: 8.6891. Min Act: -0.1700
Data Index: 5142625 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19