Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.9111. Min Act: -0.1700
Data Index: 7736059 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.9111. Min Act: -0.1700
Data Index: 8352392 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.8173. Min Act: -0.1700
Data Index: 7061553 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.7236. Min Act: -0.1700
Data Index: 2866478 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.6923. Min Act: -0.1700
Data Index: 4669700 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.6298. Min Act: -0.1700
Data Index: 35996 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5986. Min Act: -0.1700
Data Index: 3367439 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5986. Min Act: -0.1700
Data Index: 3402626 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5673. Min Act: -0.1700
Data Index: 3044195 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5673. Min Act: -0.1700
Data Index: 79981 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5673. Min Act: -0.1700
Data Index: 7322360 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5048. Min Act: -0.1700
Data Index: 8807937 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5361. Min Act: -0.1700
Data Index: 3332438 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5361. Min Act: -0.1700
Data Index: 7736060 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5673. Min Act: -0.1700
Data Index: 4713077 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5361. Min Act: -0.1700
Data Index: 2287507 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5361. Min Act: -0.1700
Data Index: 7699409 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.5048. Min Act: -0.1700
Data Index: 1017002 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.4736. Min Act: -0.1700
Data Index: 832115 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9111. Min Range: -4.9111
Max Act: 4.4423. Min Act: -0.1700
Data Index: 746920 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19