Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.8210. Min Act: -0.1700
Data Index: 5876955 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.7898. Min Act: -0.1700
Data Index: 2446271 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.6648. Min Act: -0.1700
Data Index: 1833024 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.6335. Min Act: -0.1700
Data Index: 4989952 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.5710. Min Act: -0.1700
Data Index: 7586413 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.6023. Min Act: -0.1700
Data Index: 3436930 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.5085. Min Act: -0.1700
Data Index: 8741785 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.4773. Min Act: -0.1700
Data Index: 4117218 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.4773. Min Act: -0.1700
Data Index: 2619732 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.4148. Min Act: -0.1700
Data Index: 3646618 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.4148. Min Act: -0.1700
Data Index: 4974983 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.4460. Min Act: -0.1700
Data Index: 133361 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.3835. Min Act: -0.1700
Data Index: 1711660 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.3835. Min Act: -0.1700
Data Index: 8518112 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.3835. Min Act: -0.1700
Data Index: 6269700 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.3210. Min Act: -0.1700
Data Index: 4198797 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.3210. Min Act: -0.1700
Data Index: 2521202 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.3210. Min Act: -0.1700
Data Index: 8664577 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.3210. Min Act: -0.1700
Data Index: 9492 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8210. Min Range: -6.8210
Max Act: 6.2898. Min Act: -0.1700
Data Index: 3841039 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19