Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.8901. Min Act: -0.1700
Data Index: 5750671 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.7651. Min Act: -0.1700
Data Index: 6345641 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.7026. Min Act: -0.1700
Data Index: 8646236 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6713. Min Act: -0.1700
Data Index: 5914579 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6713. Min Act: -0.1700
Data Index: 7057802 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 4598754 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6401. Min Act: -0.1700
Data Index: 6686917 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5776. Min Act: -0.1700
Data Index: 269155 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6088. Min Act: -0.1700
Data Index: 175086 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6088. Min Act: -0.1700
Data Index: 3118479 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.6088. Min Act: -0.1700
Data Index: 108147 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5776. Min Act: -0.1700
Data Index: 3268636 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5463. Min Act: -0.1700
Data Index: 7699860 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5463. Min Act: -0.1700
Data Index: 2987156 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5463. Min Act: -0.1700
Data Index: 5329773 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 6368416 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 2059100 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.4838. Min Act: -0.1700
Data Index: 3861183 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 3236596 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8901. Min Range: -4.8901
Max Act: 4.5151. Min Act: -0.1700
Data Index: 6879487 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19