Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.4061. Min Act: -0.1700
Data Index: 6360598 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.3748. Min Act: -0.1700
Data Index: 424606 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.3123. Min Act: -0.1700
Data Index: 1435831 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.3123. Min Act: -0.1700
Data Index: 4573692 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.2498. Min Act: -0.1700
Data Index: 4101257 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.2498. Min Act: -0.1700
Data Index: 5975626 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.2811. Min Act: -0.1700
Data Index: 8262494 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.2186. Min Act: -0.1700
Data Index: 8613766 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.2186. Min Act: -0.1700
Data Index: 2435508 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1873. Min Act: -0.1700
Data Index: 968065 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.2186. Min Act: -0.1700
Data Index: 7461810 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1873. Min Act: -0.1700
Data Index: 1385215 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1873. Min Act: -0.1700
Data Index: 841085 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.2186. Min Act: -0.1700
Data Index: 4680803 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1561. Min Act: -0.1700
Data Index: 5349531 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1561. Min Act: -0.1700
Data Index: 6661269 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1561. Min Act: -0.1700
Data Index: 3618817 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1248. Min Act: -0.1700
Data Index: 3809607 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1561. Min Act: -0.1700
Data Index: 7680569 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4061. Min Range: -4.4061
Max Act: 4.1561. Min Act: -0.1700
Data Index: 4922536 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19