Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0176. Min Range: -5.0176
Max Act: 5.0176. Min Act: -0.1700
Data Index: 7827291 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.9864. Min Act: -0.1700
Data Index: 6299987 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.9239. Min Act: -0.1700
Data Index: 4090894 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.9239. Min Act: -0.1700
Data Index: 2280661 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.8614. Min Act: -0.1700
Data Index: 1703076 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.8614. Min Act: -0.1700
Data Index: 8210780 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.8301. Min Act: -0.1700
Data Index: 8161759 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.8301. Min Act: -0.1700
Data Index: 1530713 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7989. Min Act: -0.1700
Data Index: 7356413 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7989. Min Act: -0.1700
Data Index: 5394537 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7676. Min Act: -0.1700
Data Index: 2354101 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7364. Min Act: -0.1700
Data Index: 7687845 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7364. Min Act: -0.1700
Data Index: 627522 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7051. Min Act: -0.1700
Data Index: 6512943 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7051. Min Act: -0.1700
Data Index: 7018203 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.7051. Min Act: -0.1700
Data Index: 745083 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.6739. Min Act: -0.1700
Data Index: 6851238 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.6739. Min Act: -0.1700
Data Index: 4435177 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.6739. Min Act: -0.1700
Data Index: 645085 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0176. Min Range: -5.0176
Max Act: 4.6739. Min Act: -0.1700
Data Index: 7061761 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19