Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5673. Min Range: -5.5673
Max Act: 5.5673. Min Act: -0.1700
Data Index: 7844680 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5673. Min Range: -5.5673
Max Act: 5.4736. Min Act: -0.1700
Data Index: 5671965 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5673. Min Range: -5.5673
Max Act: 5.0048. Min Act: -0.1700
Data Index: 6017214 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.8798. Min Act: -0.1700
Data Index: 8576654 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.8486. Min Act: -0.1700
Data Index: 6132781 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.8173. Min Act: -0.1700
Data Index: 4701156 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7861. Min Act: -0.1700
Data Index: 7341472 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7861. Min Act: -0.1700
Data Index: 7281447 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7861. Min Act: -0.1700
Data Index: 7939892 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7548. Min Act: -0.1700
Data Index: 3878185 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7548. Min Act: -0.1700
Data Index: 5139538 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7236. Min Act: -0.1700
Data Index: 5321107 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7236. Min Act: -0.1700
Data Index: 7953065 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.7236. Min Act: -0.1700
Data Index: 4447620 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.6611. Min Act: -0.1700
Data Index: 1695918 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.6611. Min Act: -0.1700
Data Index: 8806602 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.6298. Min Act: -0.1700
Data Index: 2378774 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.5673. Min Act: -0.1700
Data Index: 6782913 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.5673. Min Act: -0.1700
Data Index: 6920366 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5673. Min Range: -5.5673
Max Act: 4.5673. Min Act: -0.1700
Data Index: 6048047 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19