Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0740. Min Range: -2.0740
Max Act: 2.0740. Min Act: -0.1696
Data Index: 5390879 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9728. Min Act: -0.1700
Data Index: 7992090 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9388. Min Act: -0.1700
Data Index: 7425586 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9388. Min Act: -0.1694
Data Index: 1366192 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9388. Min Act: -0.1698
Data Index: 3545629 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9218. Min Act: -0.1679
Data Index: 2404315 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9218. Min Act: -0.1686
Data Index: 1604462 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9048. Min Act: -0.1698
Data Index: 433062 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8877. Min Act: -0.1690
Data Index: 116789 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.9048. Min Act: -0.1647
Data Index: 2256159 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8877. Min Act: -0.1697
Data Index: 6178 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8535. Min Act: -0.1700
Data Index: 1793038 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8535. Min Act: -0.1699
Data Index: 1840090 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8535. Min Act: -0.1694
Data Index: 2223827 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8192. Min Act: -0.1662
Data Index: 2192112 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8192. Min Act: -0.1686
Data Index: 7253401 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8364. Min Act: -0.1700
Data Index: 4940033 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8364. Min Act: -0.1689
Data Index: 7858906 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.7848. Min Act: -0.1689
Data Index: 5254080 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0740. Min Range: -2.0740
Max Act: 1.8192. Min Act: -0.1698
Data Index: 2404314 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19