Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.4019. Min Act: -0.1700
Data Index: 555156 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.3706. Min Act: -0.1700
Data Index: 3011195 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.3081. Min Act: -0.1700
Data Index: 2165056 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.3081. Min Act: -0.1700
Data Index: 3566916 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.2769. Min Act: -0.1700
Data Index: 5234000 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.2144. Min Act: -0.1700
Data Index: 7019172 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.1831. Min Act: -0.1700
Data Index: 7043857 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.1831. Min Act: -0.1700
Data Index: 3046141 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.1519. Min Act: -0.1700
Data Index: 1777755 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.1206. Min Act: -0.1700
Data Index: 811070 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.1206. Min Act: -0.1700
Data Index: 2739646 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.1206. Min Act: -0.1700
Data Index: 6707508 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.0894. Min Act: -0.1700
Data Index: 5188041 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.0894. Min Act: -0.1700
Data Index: 5318006 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.0581. Min Act: -0.1700
Data Index: 6729277 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.0581. Min Act: -0.1700
Data Index: 3475106 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.0581. Min Act: -0.1700
Data Index: 5768379 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.0581. Min Act: -0.1700
Data Index: 7187038 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4019. Min Range: -6.4019
Max Act: 6.0269. Min Act: -0.1700
Data Index: 1533205 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4019. Min Range: -6.4019
Max Act: 5.9956. Min Act: -0.1700
Data Index: 6014834 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19