Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.2093. Min Act: -0.1700
Data Index: 293830 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.2250. Min Act: -0.1700
Data Index: 2276632 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.1936. Min Act: -0.1700
Data Index: 8080689 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.1779. Min Act: -0.1700
Data Index: 640474 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.1779. Min Act: -0.1700
Data Index: 5577015 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.1621. Min Act: -0.1700
Data Index: 3753555 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.1464. Min Act: -0.1700
Data Index: 8378047 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0991. Min Act: -0.1700
Data Index: 8675255 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0518. Min Act: -0.1700
Data Index: 7653693 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0834. Min Act: -0.1700
Data Index: 4459079 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0834. Min Act: -0.1700
Data Index: 7826079 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0676. Min Act: -0.1700
Data Index: 8089969 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0834. Min Act: -0.1700
Data Index: 4761419 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0834. Min Act: -0.1700
Data Index: 6430541 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0676. Min Act: -0.1700
Data Index: 7512618 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0518. Min Act: -0.1700
Data Index: 800061 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0044. Min Act: -0.1700
Data Index: 2855859 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0202. Min Act: -0.1700
Data Index: 2449894 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2250. Min Range: -3.2250
Max Act: 2.9886. Min Act: -0.1700
Data Index: 6827140 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2250. Min Range: -3.2250
Max Act: 3.0044. Min Act: -0.1700
Data Index: 1062718 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19