Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4958 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.2984. Min Act: -0.1700
Data Index: 3488867 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.2047. Min Act: -0.1700
Data Index: 3847021 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.1109. Min Act: -0.1700
Data Index: 8456177 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.0797. Min Act: -0.1700
Data Index: 3570402 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.0172. Min Act: -0.1700
Data Index: 6492593 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.9859. Min Act: -0.1700
Data Index: 2470473 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.9547. Min Act: -0.1700
Data Index: 2188516 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.9234. Min Act: -0.1700
Data Index: 6191910 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8922. Min Act: -0.1700
Data Index: 5809133 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8297. Min Act: -0.1700
Data Index: 1877777 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8297. Min Act: -0.1700
Data Index: 923118 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 8203349 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 1699164 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 4509203 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 1482362 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 2472987 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 5608515 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7672. Min Act: -0.1700
Data Index: 6456290 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7359. Min Act: -0.1700
Data Index: 6957312 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7359. Min Act: -0.1700
Data Index: 7299115 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19