Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9858. Min Act: -0.1700
Data Index: 3308959 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9546. Min Act: -0.1700
Data Index: 4065837 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 7519746 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9546. Min Act: -0.1700
Data Index: 5832415 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 4620170 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 4958060 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 8404284 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 1259035 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.8920. Min Act: -0.1700
Data Index: 4082520 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 4554879 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 5615823 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 8510933 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 2785643 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.8608. Min Act: -0.1700
Data Index: 4137907 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.9233. Min Act: -0.1700
Data Index: 7206998 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.8920. Min Act: -0.1700
Data Index: 5436433 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.8608. Min Act: -0.1700
Data Index: 6265046 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.8608. Min Act: -0.1700
Data Index: 3795224 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.8608. Min Act: -0.1700
Data Index: 206003 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9858. Min Range: -3.9858
Max Act: 3.8295. Min Act: -0.1700
Data Index: 8251139 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19