Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0111. Min Range: -6.0111
Max Act: 6.0111. Min Act: -0.1700
Data Index: 6512194 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.8861. Min Act: -0.1700
Data Index: 7022264 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.9486. Min Act: -0.1700
Data Index: 5044267 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.8548. Min Act: -0.1700
Data Index: 5795666 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.8861. Min Act: -0.1700
Data Index: 4328715 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.8236. Min Act: -0.1700
Data Index: 7017088 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3889363 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.6673. Min Act: -0.1700
Data Index: 480139 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3732966 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.6361. Min Act: -0.1700
Data Index: 8120001 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5736. Min Act: -0.1700
Data Index: 2703501 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5736. Min Act: -0.1700
Data Index: 8572170 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5736. Min Act: -0.1700
Data Index: 6397583 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5423. Min Act: -0.1700
Data Index: 5004343 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5423. Min Act: -0.1700
Data Index: 464844 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5736. Min Act: -0.1700
Data Index: 3248967 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5111. Min Act: -0.1700
Data Index: 3855045 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5736. Min Act: -0.1700
Data Index: 5909730 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5111. Min Act: -0.1700
Data Index: 3631087 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0111. Min Range: -6.0111
Max Act: 5.5111. Min Act: -0.1700
Data Index: 6392586 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19