Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0751. Min Range: -7.0751
Max Act: 7.0751. Min Act: -0.1700
Data Index: 559251 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.9501. Min Act: -0.1700
Data Index: 559252 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.8564. Min Act: -0.1700
Data Index: 7324841 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.7626. Min Act: -0.1700
Data Index: 7009112 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.7314. Min Act: -0.1700
Data Index: 8745505 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.5751. Min Act: -0.1700
Data Index: 7745630 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.5751. Min Act: -0.1700
Data Index: 1885317 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.4814. Min Act: -0.1700
Data Index: 7052331 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.4501. Min Act: -0.1700
Data Index: 3538119 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.3251. Min Act: -0.1700
Data Index: 3772138 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.3876. Min Act: -0.1700
Data Index: 4034414 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.3564. Min Act: -0.1700
Data Index: 1661593 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.3251. Min Act: -0.1700
Data Index: 1925340 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.3251. Min Act: -0.1700
Data Index: 7818943 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.3251. Min Act: -0.1700
Data Index: 632217 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.3251. Min Act: -0.1700
Data Index: 3083914 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.2939. Min Act: -0.1700
Data Index: 984749 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.2939. Min Act: -0.1700
Data Index: 7929652 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.2939. Min Act: -0.1700
Data Index: 3772127 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0751. Min Range: -7.0751
Max Act: 6.2939. Min Act: -0.1700
Data Index: 4310514 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19