Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2783. Min Range: -6.2783
Max Act: 6.2783. Min Act: -0.1700
Data Index: 3253896 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2783. Min Range: -6.2783
Max Act: 6.2158. Min Act: -0.1700
Data Index: 1643111 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2783. Min Range: -6.2783
Max Act: 6.0908. Min Act: -0.1700
Data Index: 6998450 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2783. Min Range: -6.2783
Max Act: 6.0595. Min Act: -0.1700
Data Index: 7013454 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.9658. Min Act: -0.1700
Data Index: 2849968 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.9033. Min Act: -0.1700
Data Index: 8522792 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.9033. Min Act: -0.1700
Data Index: 4604026 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8408. Min Act: -0.1700
Data Index: 2542044 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8408. Min Act: -0.1700
Data Index: 2471378 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8720. Min Act: -0.1700
Data Index: 613331 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8408. Min Act: -0.1700
Data Index: 3798362 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8408. Min Act: -0.1700
Data Index: 8064785 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8408. Min Act: -0.1700
Data Index: 8312146 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8095. Min Act: -0.1700
Data Index: 1684917 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.7783. Min Act: -0.1700
Data Index: 707795 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8095. Min Act: -0.1700
Data Index: 8680228 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.8095. Min Act: -0.1700
Data Index: 7935247 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.7783. Min Act: -0.1700
Data Index: 8656016 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.7783. Min Act: -0.1700
Data Index: 2077879 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2783. Min Range: -6.2783
Max Act: 5.7783. Min Act: -0.1700
Data Index: 5894512 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19