Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1660 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.7519. Min Act: -0.1700
Data Index: 2284536 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.7206. Min Act: -0.1700
Data Index: 7817171 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.6894. Min Act: -0.1700
Data Index: 7483025 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.6581. Min Act: -0.1700
Data Index: 7392855 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.6269. Min Act: -0.1700
Data Index: 5238859 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.6269. Min Act: -0.1700
Data Index: 6125172 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5956. Min Act: -0.1700
Data Index: 5372347 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5956. Min Act: -0.1700
Data Index: 5099846 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5956. Min Act: -0.1700
Data Index: 7638696 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5956. Min Act: -0.1700
Data Index: 6227171 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5956. Min Act: -0.1700
Data Index: 8254421 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5331. Min Act: -0.1700
Data Index: 7638698 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5331. Min Act: -0.1700
Data Index: 7778924 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5644. Min Act: -0.1700
Data Index: 7812659 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5331. Min Act: -0.1700
Data Index: 246582 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5331. Min Act: -0.1700
Data Index: 7220109 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5019. Min Act: -0.1700
Data Index: 140508 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5019. Min Act: -0.1700
Data Index: 3321325 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.4706. Min Act: -0.1700
Data Index: 7183721 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7519. Min Range: -5.7519
Max Act: 5.5019. Min Act: -0.1700
Data Index: 8331029 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19