Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4962. Min Range: -7.4962
Max Act: 7.4962. Min Act: -0.1700
Data Index: 1772072 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4962. Min Range: -7.4962
Max Act: 7.4025. Min Act: -0.1700
Data Index: 440049 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4962. Min Range: -7.4962
Max Act: 7.2775. Min Act: -0.1700
Data Index: 5951104 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4962. Min Range: -7.4962
Max Act: 7.0275. Min Act: -0.1700
Data Index: 7654279 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4962. Min Range: -7.4962
Max Act: 7.0275. Min Act: -0.1700
Data Index: 4052308 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.9962. Min Act: -0.1700
Data Index: 1393352 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.8712. Min Act: -0.1700
Data Index: 6991059 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.8400. Min Act: -0.1700
Data Index: 1606479 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.8087. Min Act: -0.1700
Data Index: 653630 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.8087. Min Act: -0.1700
Data Index: 3946335 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.7775. Min Act: -0.1700
Data Index: 2687737 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.7775. Min Act: -0.1700
Data Index: 8296899 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6837. Min Act: -0.1700
Data Index: 4776741 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6837. Min Act: -0.1700
Data Index: 7711425 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6525. Min Act: -0.1700
Data Index: 3953938 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6837. Min Act: -0.1700
Data Index: 266454 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6837. Min Act: -0.1700
Data Index: 5773750 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6525. Min Act: -0.1700
Data Index: 3701106 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6525. Min Act: -0.1700
Data Index: 4896802 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4962. Min Range: -7.4962
Max Act: 6.6525. Min Act: -0.1700
Data Index: 5969122 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19