Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2058 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.9760. Min Act: -0.1700
Data Index: 8086440 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7884. Min Act: -0.1700
Data Index: 7139385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7884. Min Act: -0.1700
Data Index: 8164685 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7884. Min Act: -0.1700
Data Index: 5833575 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7884. Min Act: -0.1700
Data Index: 4599747 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.7884. Min Act: -0.1700
Data Index: 6871149 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6945. Min Act: -0.1700
Data Index: 3142944 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6633. Min Act: -0.1700
Data Index: 3855094 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6633. Min Act: -0.1700
Data Index: 1236150 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6320. Min Act: -0.1700
Data Index: 6690206 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6320. Min Act: -0.1700
Data Index: 5608248 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6320. Min Act: -0.1700
Data Index: 5805589 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.6007. Min Act: -0.1700
Data Index: 7809498 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5694. Min Act: -0.1700
Data Index: 3176311 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5694. Min Act: -0.1700
Data Index: 1893896 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5694. Min Act: -0.1700
Data Index: 5467812 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5694. Min Act: -0.1700
Data Index: 1896915 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5694. Min Act: -0.1700
Data Index: 1900914 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5694. Min Act: -0.1700
Data Index: 6990743 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9760. Min Range: -3.9760
Max Act: 3.5380. Min Act: -0.1700
Data Index: 2182951 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19