Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.5798. Min Act: -0.1700
Data Index: 370130 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.5173. Min Act: -0.1700
Data Index: 4193051 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.3923. Min Act: -0.1700
Data Index: 8035114 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.3610. Min Act: -0.1700
Data Index: 6724146 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.3610. Min Act: -0.1700
Data Index: 1584673 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.3298. Min Act: -0.1700
Data Index: 5664655 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2985. Min Act: -0.1700
Data Index: 7982416 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2985. Min Act: -0.1700
Data Index: 8488303 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2673. Min Act: -0.1700
Data Index: 5636712 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2985. Min Act: -0.1700
Data Index: 2147752 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2360. Min Act: -0.1700
Data Index: 4110864 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2673. Min Act: -0.1700
Data Index: 723892 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2360. Min Act: -0.1700
Data Index: 1018058 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2048. Min Act: -0.1700
Data Index: 8570972 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2048. Min Act: -0.1700
Data Index: 5192039 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2048. Min Act: -0.1700
Data Index: 8108951 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.2048. Min Act: -0.1700
Data Index: 5381409 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.1735. Min Act: -0.1700
Data Index: 996094 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.1735. Min Act: -0.1700
Data Index: 5673685 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5798. Min Range: -6.5798
Max Act: 6.1735. Min Act: -0.1700
Data Index: 1537637 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19