Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1262. Min Range: -4.1262
Max Act: 4.1262. Min Act: -0.1700
Data Index: 2120451 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1262. Min Range: -4.1262
Max Act: 4.0012. Min Act: -0.1700
Data Index: 4273919 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.9074. Min Act: -0.1700
Data Index: 387785 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.8761. Min Act: -0.1700
Data Index: 7353639 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.8761. Min Act: -0.1700
Data Index: 1571547 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.8761. Min Act: -0.1700
Data Index: 2353451 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.8449. Min Act: -0.1700
Data Index: 5389372 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.8136. Min Act: -0.1700
Data Index: 5449265 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.8136. Min Act: -0.1700
Data Index: 7095249 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.8449. Min Act: -0.1700
Data Index: 8163359 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7823. Min Act: -0.1700
Data Index: 6133728 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7510. Min Act: -0.1700
Data Index: 3700594 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7823. Min Act: -0.1700
Data Index: 4636172 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7823. Min Act: -0.1700
Data Index: 1176468 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7823. Min Act: -0.1700
Data Index: 5623756 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7510. Min Act: -0.1700
Data Index: 2597540 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7197. Min Act: -0.1700
Data Index: 6323353 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7510. Min Act: -0.1700
Data Index: 4883259 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7510. Min Act: -0.1700
Data Index: 3020153 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1262. Min Range: -4.1262
Max Act: 3.7197. Min Act: -0.1700
Data Index: 120259 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19