Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 381 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2153. Min Range: -7.2153
Max Act: 7.2153. Min Act: -0.1700
Data Index: 6411352 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.9966. Min Act: -0.1700
Data Index: 6908902 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.9341. Min Act: -0.1700
Data Index: 2686443 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8716. Min Act: -0.1700
Data Index: 7670789 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8091. Min Act: -0.1700
Data Index: 4526830 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7153. Min Act: -0.1700
Data Index: 7958248 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7153. Min Act: -0.1700
Data Index: 7070696 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7153. Min Act: -0.1700
Data Index: 7070706 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6841. Min Act: -0.1700
Data Index: 6908900 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6841. Min Act: -0.1700
Data Index: 4142428 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6841. Min Act: -0.1700
Data Index: 1608415 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6216. Min Act: -0.1700
Data Index: 8625320 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6216. Min Act: -0.1700
Data Index: 2122802 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6216. Min Act: -0.1700
Data Index: 2572978 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.5903. Min Act: -0.1700
Data Index: 2957362 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.5903. Min Act: -0.1700
Data Index: 7605401 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6216. Min Act: -0.1700
Data Index: 5062817 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.5591. Min Act: -0.1700
Data Index: 2957360 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.5278. Min Act: -0.1700
Data Index: 4019790 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.5591. Min Act: -0.1700
Data Index: 4604254 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19