Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.9858. Min Act: -0.1700
Data Index: 3302746 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.9340. Min Act: -0.1700
Data Index: 1606452 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.9169. Min Act: -0.1700
Data Index: 38952 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8997. Min Act: -0.1700
Data Index: 7970515 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8997. Min Act: -0.1700
Data Index: 4875757 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8997. Min Act: -0.1700
Data Index: 3273371 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8826. Min Act: -0.1700
Data Index: 3017884 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8826. Min Act: -0.1700
Data Index: 1633012 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8656. Min Act: -0.1700
Data Index: 4698238 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8486. Min Act: -0.1700
Data Index: 121880 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.8149. Min Act: -0.1700
Data Index: 7921696 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7981. Min Act: -0.1700
Data Index: 5258304 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7981. Min Act: -0.1700
Data Index: 1938178 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7981. Min Act: -0.1700
Data Index: 5060423 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7981. Min Act: -0.1700
Data Index: 4386238 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7981. Min Act: -0.1700
Data Index: 1644282 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7813. Min Act: -0.1700
Data Index: 5190857 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7813. Min Act: -0.1700
Data Index: 1301930 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7647. Min Act: -0.1700
Data Index: 487769 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9858. Min Range: -0.9858
Max Act: 0.7647. Min Act: -0.1700
Data Index: 640895 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19