Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.3571. Min Act: -0.1700
Data Index: 5551856 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.2946. Min Act: -0.1700
Data Index: 6261863 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0446. Min Act: -0.1700
Data Index: 8361813 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.8883. Min Act: -0.1700
Data Index: 3105796 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7946. Min Act: -0.1700
Data Index: 5633415 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7946. Min Act: -0.1700
Data Index: 5714852 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7633. Min Act: -0.1700
Data Index: 859143 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7321. Min Act: -0.1700
Data Index: 2050531 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7321. Min Act: -0.1700
Data Index: 2817423 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4690511 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4184260 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3851199 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.6696. Min Act: -0.1700
Data Index: 2483554 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3808336 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.6383. Min Act: -0.1700
Data Index: 642713 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.6383. Min Act: -0.1700
Data Index: 1840750 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.6071. Min Act: -0.1700
Data Index: 8780057 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.5758. Min Act: -0.1700
Data Index: 5693979 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.5758. Min Act: -0.1700
Data Index: 6219510 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.5758. Min Act: -0.1700
Data Index: 182960 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19