Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1515 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0722. Min Range: -2.0722
Max Act: 2.0722. Min Act: -0.1699
Data Index: 3138531 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9879. Min Act: -0.1700
Data Index: 8068980 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9879. Min Act: -0.1699
Data Index: 5385959 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9540. Min Act: -0.1700
Data Index: 8427659 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9710. Min Act: -0.1700
Data Index: 655566 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9540. Min Act: -0.1699
Data Index: 965647 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9540. Min Act: -0.1700
Data Index: 645106 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9370. Min Act: -0.1700
Data Index: 7866844 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9710. Min Act: -0.1699
Data Index: 155651 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9370. Min Act: -0.1700
Data Index: 1318291 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9370. Min Act: -0.1700
Data Index: 3001895 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9370. Min Act: -0.1700
Data Index: 4427477 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9370. Min Act: -0.1699
Data Index: 8296706 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9370. Min Act: -0.1700
Data Index: 4685204 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9370. Min Act: -0.1700
Data Index: 6365418 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9200. Min Act: -0.1700
Data Index: 6930954 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9200. Min Act: -0.1699
Data Index: 109857 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9200. Min Act: -0.1700
Data Index: 6645564 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9200. Min Act: -0.1700
Data Index: 4488587 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0722. Min Range: -2.0722
Max Act: 1.9030. Min Act: -0.1700
Data Index: 4799355 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19