Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 429 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.4611. Min Act: -0.1700
Data Index: 5291053 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.2424. Min Act: -0.1700
Data Index: 6865334 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.2111. Min Act: -0.1700
Data Index: 7672178 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.2111. Min Act: -0.1700
Data Index: 5729475 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.1799. Min Act: -0.1700
Data Index: 4359184 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.1174. Min Act: -0.1700
Data Index: 4655621 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.1486. Min Act: -0.1700
Data Index: 7354665 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.1486. Min Act: -0.1700
Data Index: 4237706 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.1174. Min Act: -0.1700
Data Index: 4199826 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.1174. Min Act: -0.1700
Data Index: 6832936 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0549. Min Act: -0.1700
Data Index: 5488632 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0861. Min Act: -0.1700
Data Index: 7013816 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0861. Min Act: -0.1700
Data Index: 2300828 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.1174. Min Act: -0.1700
Data Index: 2816169 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0861. Min Act: -0.1700
Data Index: 2442857 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0549. Min Act: -0.1700
Data Index: 1520825 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0861. Min Act: -0.1700
Data Index: 3058402 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0549. Min Act: -0.1700
Data Index: 7875280 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0549. Min Act: -0.1700
Data Index: 3504865 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4611. Min Range: -5.4611
Max Act: 5.0549. Min Act: -0.1700
Data Index: 438760 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19