Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3744. Min Range: -8.3744
Max Act: 8.3744. Min Act: -0.1700
Data Index: 5243023 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3744. Min Range: -8.3744
Max Act: 7.0931. Min Act: -0.1700
Data Index: 6818764 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3744. Min Range: -8.3744
Max Act: 7.0931. Min Act: -0.1700
Data Index: 3907071 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.7494. Min Act: -0.1700
Data Index: 2698030 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6869. Min Act: -0.1700
Data Index: 8374003 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6556. Min Act: -0.1700
Data Index: 3859293 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6869. Min Act: -0.1700
Data Index: 8308127 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6556. Min Act: -0.1700
Data Index: 196133 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6556. Min Act: -0.1700
Data Index: 7830019 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6556. Min Act: -0.1700
Data Index: 7916758 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6556. Min Act: -0.1700
Data Index: 7290539 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.6244. Min Act: -0.1700
Data Index: 4050618 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5931. Min Act: -0.1700
Data Index: 4331256 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5619. Min Act: -0.1700
Data Index: 4701031 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5619. Min Act: -0.1700
Data Index: 691824 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5306. Min Act: -0.1700
Data Index: 608361 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5306. Min Act: -0.1700
Data Index: 351680 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5306. Min Act: -0.1700
Data Index: 16360 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5306. Min Act: -0.1700
Data Index: 8097228 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3744. Min Range: -8.3744
Max Act: 6.5306. Min Act: -0.1700
Data Index: 7735020 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19