Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.4370. Min Act: -0.1700
Data Index: 7618746 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.4683. Min Act: -0.1700
Data Index: 1656978 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.4058. Min Act: -0.1700
Data Index: 6693975 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.3433. Min Act: -0.1700
Data Index: 5433750 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.3433. Min Act: -0.1700
Data Index: 6105114 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.3120. Min Act: -0.1700
Data Index: 3883051 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.2808. Min Act: -0.1700
Data Index: 4144412 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.1870. Min Act: -0.1700
Data Index: 65949 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.1870. Min Act: -0.1700
Data Index: 7675560 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.1558. Min Act: -0.1700
Data Index: 5255999 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.1558. Min Act: -0.1700
Data Index: 6485291 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.1245. Min Act: -0.1700
Data Index: 7193381 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.1245. Min Act: -0.1700
Data Index: 358970 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.0933. Min Act: -0.1700
Data Index: 3450762 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.0933. Min Act: -0.1700
Data Index: 4602434 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.0620. Min Act: -0.1700
Data Index: 4077715 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.0933. Min Act: -0.1700
Data Index: 4571834 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.0933. Min Act: -0.1700
Data Index: 323914 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.0308. Min Act: -0.1700
Data Index: 5850609 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4683. Min Range: -6.4683
Max Act: 6.0308. Min Act: -0.1700
Data Index: 5073825 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19