Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.4734. Min Act: -0.1700
Data Index: 2548022 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.4422. Min Act: -0.1700
Data Index: 1579749 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.3797. Min Act: -0.1700
Data Index: 5584153 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.3797. Min Act: -0.1700
Data Index: 6151526 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.3797. Min Act: -0.1700
Data Index: 2401171 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.3484. Min Act: -0.1700
Data Index: 5456665 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.2859. Min Act: -0.1700
Data Index: 1716765 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.2547. Min Act: -0.1700
Data Index: 4618354 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.1922. Min Act: -0.1700
Data Index: 8549996 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.1922. Min Act: -0.1700
Data Index: 3706977 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.1922. Min Act: -0.1700
Data Index: 5826580 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.1922. Min Act: -0.1700
Data Index: 2748133 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.1297. Min Act: -0.1700
Data Index: 6782747 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.0672. Min Act: -0.1700
Data Index: 6767031 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.0984. Min Act: -0.1700
Data Index: 4661214 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.0984. Min Act: -0.1700
Data Index: 256620 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.0984. Min Act: -0.1700
Data Index: 2827395 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.0672. Min Act: -0.1700
Data Index: 5251343 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.0672. Min Act: -0.1700
Data Index: 2865658 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4734. Min Range: -5.4734
Max Act: 5.0672. Min Act: -0.1700
Data Index: 7700830 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19