Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1511. Min Range: -9.1511
Max Act: 9.1511. Min Act: -0.1700
Data Index: 7973779 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.9011. Min Act: -0.1700
Data Index: 2254235 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.8386. Min Act: -0.1700
Data Index: 1306441 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.7761. Min Act: -0.1700
Data Index: 2201917 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.7136. Min Act: -0.1700
Data Index: 1672021 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.7136. Min Act: -0.1700
Data Index: 7812407 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.7136. Min Act: -0.1700
Data Index: 7320259 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.6511. Min Act: -0.1700
Data Index: 7945786 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.6511. Min Act: -0.1700
Data Index: 4982820 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5886. Min Act: -0.1700
Data Index: 5410278 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5886. Min Act: -0.1700
Data Index: 242073 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5886. Min Act: -0.1700
Data Index: 8608177 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5886. Min Act: -0.1700
Data Index: 1575804 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5886. Min Act: -0.1700
Data Index: 3989348 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5261. Min Act: -0.1700
Data Index: 977732 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5886. Min Act: -0.1700
Data Index: 1025625 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5261. Min Act: -0.1700
Data Index: 45394 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5261. Min Act: -0.1700
Data Index: 7323503 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5261. Min Act: -0.1700
Data Index: 2720332 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1511. Min Range: -9.1511
Max Act: 8.5261. Min Act: -0.1700
Data Index: 2948491 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19