Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4126. Min Range: -8.4126
Max Act: 8.4126. Min Act: -0.1700
Data Index: 4206252 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4126. Min Range: -8.4126
Max Act: 8.1001. Min Act: -0.1700
Data Index: 5444958 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.8501. Min Act: -0.1700
Data Index: 6528205 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.7563. Min Act: -0.1700
Data Index: 4780540 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.6938. Min Act: -0.1700
Data Index: 7789166 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.6938. Min Act: -0.1700
Data Index: 2275650 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.6313. Min Act: -0.1700
Data Index: 210268 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.6313. Min Act: -0.1700
Data Index: 3554535 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.6313. Min Act: -0.1700
Data Index: 5064204 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.6313. Min Act: -0.1700
Data Index: 3653793 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.6001. Min Act: -0.1700
Data Index: 4781459 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.5063. Min Act: -0.1700
Data Index: 3355178 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.5063. Min Act: -0.1700
Data Index: 7349862 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.4751. Min Act: -0.1700
Data Index: 7061744 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.4751. Min Act: -0.1700
Data Index: 4188291 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.4438. Min Act: -0.1700
Data Index: 1128105 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.4126. Min Act: -0.1700
Data Index: 7143353 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.3813. Min Act: -0.1700
Data Index: 3518658 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.3813. Min Act: -0.1700
Data Index: 1165123 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4126. Min Range: -8.4126
Max Act: 7.3501. Min Act: -0.1700
Data Index: 5065314 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19