Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.3097. Min Act: -0.1700
Data Index: 6880504 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.3097. Min Act: -0.1700
Data Index: 63920 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.2785. Min Act: -0.1700
Data Index: 7136961 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.2785. Min Act: -0.1700
Data Index: 2169309 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.2785. Min Act: -0.1700
Data Index: 6407250 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.1847. Min Act: -0.1700
Data Index: 7819653 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.1535. Min Act: -0.1700
Data Index: 5442690 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.0910. Min Act: -0.1700
Data Index: 1034593 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.0597. Min Act: -0.1700
Data Index: 6794654 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3097. Min Range: -7.3097
Max Act: 7.0285. Min Act: -0.1700
Data Index: 4118696 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9972. Min Act: -0.1700
Data Index: 4678168 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9660. Min Act: -0.1700
Data Index: 5465719 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9660. Min Act: -0.1700
Data Index: 7748209 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9660. Min Act: -0.1700
Data Index: 957081 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9972. Min Act: -0.1700
Data Index: 6280262 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9972. Min Act: -0.1700
Data Index: 5297025 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9660. Min Act: -0.1700
Data Index: 576651 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9660. Min Act: -0.1700
Data Index: 6038873 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9347. Min Act: -0.1700
Data Index: 4067095 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3097. Min Range: -7.3097
Max Act: 6.9347. Min Act: -0.1700
Data Index: 2861105 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19