Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.3067. Min Act: -0.1700
Data Index: 5066220 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.2753. Min Act: -0.1700
Data Index: 602594 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.1338. Min Act: -0.1700
Data Index: 6588431 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.1495. Min Act: -0.1700
Data Index: 6668151 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.1338. Min Act: -0.1700
Data Index: 2459627 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0865. Min Act: -0.1700
Data Index: 670182 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0865. Min Act: -0.1700
Data Index: 7761612 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.1023. Min Act: -0.1700
Data Index: 5606407 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0865. Min Act: -0.1700
Data Index: 95732 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0392. Min Act: -0.1700
Data Index: 1737080 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0550. Min Act: -0.1700
Data Index: 3703263 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0392. Min Act: -0.1700
Data Index: 4301427 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0550. Min Act: -0.1700
Data Index: 8074679 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0234. Min Act: -0.1700
Data Index: 6307665 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0392. Min Act: -0.1700
Data Index: 2024165 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0392. Min Act: -0.1700
Data Index: 3714270 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0076. Min Act: -0.1700
Data Index: 2024926 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0076. Min Act: -0.1700
Data Index: 1113292 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0234. Min Act: -0.1700
Data Index: 4733178 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3067. Min Range: -3.3067
Max Act: 3.0076. Min Act: -0.1700
Data Index: 4300577 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19