Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0763. Min Range: -6.0763
Max Act: 6.0763. Min Act: -0.1700
Data Index: 7994753 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9513. Min Act: -0.1700
Data Index: 1806892 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9513. Min Act: -0.1700
Data Index: 1892544 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9200. Min Act: -0.1700
Data Index: 1577203 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8888. Min Act: -0.1700
Data Index: 4796525 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9200. Min Act: -0.1700
Data Index: 3358236 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9200. Min Act: -0.1700
Data Index: 408817 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9200. Min Act: -0.1700
Data Index: 5884322 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9200. Min Act: -0.1700
Data Index: 1196241 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8888. Min Act: -0.1700
Data Index: 6978807 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.9200. Min Act: -0.1700
Data Index: 8397369 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8888. Min Act: -0.1700
Data Index: 2427326 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8888. Min Act: -0.1700
Data Index: 7933730 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8575. Min Act: -0.1700
Data Index: 3358521 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8575. Min Act: -0.1700
Data Index: 8069835 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8575. Min Act: -0.1700
Data Index: 4202626 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.7950. Min Act: -0.1700
Data Index: 2468389 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8263. Min Act: -0.1700
Data Index: 2598020 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8263. Min Act: -0.1700
Data Index: 5566009 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0763. Min Range: -6.0763
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3619001 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19