Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3646. Min Range: -7.3646
Max Act: 7.3646. Min Act: -0.1700
Data Index: 4908006 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.7708. Min Act: -0.1700
Data Index: 5056524 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.7083. Min Act: -0.1700
Data Index: 7891723 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.6458. Min Act: -0.1700
Data Index: 1574876 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.6458. Min Act: -0.1700
Data Index: 8741327 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.6146. Min Act: -0.1700
Data Index: 4757227 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.4896. Min Act: -0.1700
Data Index: 4276343 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.4583. Min Act: -0.1700
Data Index: 5652928 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3958. Min Act: -0.1700
Data Index: 3576051 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3958. Min Act: -0.1700
Data Index: 1245194 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3958. Min Act: -0.1700
Data Index: 2855461 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3333. Min Act: -0.1700
Data Index: 3174187 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3333. Min Act: -0.1700
Data Index: 2231656 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3333. Min Act: -0.1700
Data Index: 2460654 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3646. Min Act: -0.1700
Data Index: 8746782 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3021. Min Act: -0.1700
Data Index: 1730023 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.3333. Min Act: -0.1700
Data Index: 2523899 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.2396. Min Act: -0.1700
Data Index: 8783042 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.2396. Min Act: -0.1700
Data Index: 3852594 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3646. Min Range: -7.3646
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7891722 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19