Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.9958. Min Act: -0.1700
Data Index: 6344602 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.8707. Min Act: -0.1700
Data Index: 5796824 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.9020. Min Act: -0.1700
Data Index: 3026717 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.8394. Min Act: -0.1700
Data Index: 7575233 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.8394. Min Act: -0.1700
Data Index: 2607563 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.8394. Min Act: -0.1700
Data Index: 1752370 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.8707. Min Act: -0.1700
Data Index: 1924180 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.7769. Min Act: -0.1700
Data Index: 437664 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.8082. Min Act: -0.1700
Data Index: 8152611 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.8394. Min Act: -0.1700
Data Index: 311180 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.7769. Min Act: -0.1700
Data Index: 6546527 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.7143. Min Act: -0.1700
Data Index: 890032 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.7456. Min Act: -0.1700
Data Index: 8404977 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.7456. Min Act: -0.1700
Data Index: 3963615 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.7456. Min Act: -0.1700
Data Index: 5220868 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.6830. Min Act: -0.1700
Data Index: 5854865 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.6830. Min Act: -0.1700
Data Index: 1495553 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.6830. Min Act: -0.1700
Data Index: 2951424 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.6830. Min Act: -0.1700
Data Index: 8473938 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9958. Min Range: -3.9958
Max Act: 3.6830. Min Act: -0.1700
Data Index: 4001595 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19