Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 825 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.9726. Min Act: -0.1700
Data Index: 3699822 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.8140. Min Act: -0.1700
Data Index: 8114643 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5577. Min Act: -0.1700
Data Index: 5376104 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5415. Min Act: -0.1700
Data Index: 3348667 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5415. Min Act: -0.1700
Data Index: 574877 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5415. Min Act: -0.1700
Data Index: 401554 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5254. Min Act: -0.1700
Data Index: 8659874 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5092. Min Act: -0.1700
Data Index: 6259106 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5092. Min Act: -0.1700
Data Index: 279728 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4930. Min Act: -0.1700
Data Index: 7875025 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.5092. Min Act: -0.1700
Data Index: 2723714 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4930. Min Act: -0.1700
Data Index: 1344953 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4930. Min Act: -0.1700
Data Index: 3508054 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4605. Min Act: -0.1700
Data Index: 3847614 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4605. Min Act: -0.1700
Data Index: 739557 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4605. Min Act: -0.1700
Data Index: 4404205 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4768. Min Act: -0.1700
Data Index: 8010387 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4443. Min Act: -0.1700
Data Index: 797677 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4443. Min Act: -0.1700
Data Index: 4609896 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9726. Min Range: -2.9726
Max Act: 2.4443. Min Act: -0.1700
Data Index: 6394961 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19