Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.5816. Min Act: -0.1700
Data Index: 5685618 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.3941. Min Act: -0.1700
Data Index: 8332557 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.3316. Min Act: -0.1700
Data Index: 5290978 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.3316. Min Act: -0.1700
Data Index: 5043176 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.2691. Min Act: -0.1700
Data Index: 4183290 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.2066. Min Act: -0.1700
Data Index: 349920 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.2066. Min Act: -0.1700
Data Index: 5003897 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.2066. Min Act: -0.1700
Data Index: 548165 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.1441. Min Act: -0.1700
Data Index: 7328081 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 2791894 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 3493391 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 7022842 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 6533929 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 8747788 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 4998731 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 1380548 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 720344 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0816. Min Act: -0.1700
Data Index: 4361875 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0191. Min Act: -0.1700
Data Index: 7279707 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5816. Min Range: -8.5816
Max Act: 8.0191. Min Act: -0.1700
Data Index: 1849399 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19