Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0896. Min Range: -8.0896
Max Act: 8.0896. Min Act: -0.1700
Data Index: 3409693 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.8396. Min Act: -0.1700
Data Index: 3067685 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.7458. Min Act: -0.1700
Data Index: 3405682 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.7771. Min Act: -0.1700
Data Index: 669281 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.7771. Min Act: -0.1700
Data Index: 4072865 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.7771. Min Act: -0.1700
Data Index: 1920310 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.7771. Min Act: -0.1700
Data Index: 6897796 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.7146. Min Act: -0.1700
Data Index: 5218845 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6833. Min Act: -0.1700
Data Index: 1001930 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6833. Min Act: -0.1700
Data Index: 4397520 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6521. Min Act: -0.1700
Data Index: 3821603 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6833. Min Act: -0.1700
Data Index: 217227 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6521. Min Act: -0.1700
Data Index: 8772732 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6521. Min Act: -0.1700
Data Index: 7480502 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6521. Min Act: -0.1700
Data Index: 3047031 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.5896. Min Act: -0.1700
Data Index: 7162247 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6208. Min Act: -0.1700
Data Index: 5595331 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.6521. Min Act: -0.1700
Data Index: 313937 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.5896. Min Act: -0.1700
Data Index: 308378 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0896. Min Range: -8.0896
Max Act: 7.5896. Min Act: -0.1700
Data Index: 6905788 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19