Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.4128. Min Act: -0.1700
Data Index: 8818333 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.3191. Min Act: -0.1700
Data Index: 1394482 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.2566. Min Act: -0.1700
Data Index: 5534398 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.2253. Min Act: -0.1700
Data Index: 3548484 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.0378. Min Act: -0.1700
Data Index: 5258618 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.0378. Min Act: -0.1700
Data Index: 521400 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.0066. Min Act: -0.1700
Data Index: 4164981 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4128. Min Range: -6.4128
Max Act: 6.0066. Min Act: -0.1700
Data Index: 8796814 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.9753. Min Act: -0.1700
Data Index: 772242 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.9441. Min Act: -0.1700
Data Index: 8331554 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.9128. Min Act: -0.1700
Data Index: 1655418 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8816. Min Act: -0.1700
Data Index: 780084 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8816. Min Act: -0.1700
Data Index: 7088376 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8816. Min Act: -0.1700
Data Index: 2628028 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.9128. Min Act: -0.1700
Data Index: 4660629 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8816. Min Act: -0.1700
Data Index: 404586 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8816. Min Act: -0.1700
Data Index: 4740089 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8816. Min Act: -0.1700
Data Index: 6696861 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8191. Min Act: -0.1700
Data Index: 4315410 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4128. Min Range: -6.4128
Max Act: 5.8503. Min Act: -0.1700
Data Index: 2629955 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19