Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5747 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.8911. Min Act: -0.1700
Data Index: 640868 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.8286. Min Act: -0.1700
Data Index: 6959400 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7347. Min Act: -0.1700
Data Index: 4406052 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7660. Min Act: -0.1700
Data Index: 640866 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7660. Min Act: -0.1700
Data Index: 2423936 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7347. Min Act: -0.1700
Data Index: 640867 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7034. Min Act: -0.1700
Data Index: 2198051 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7034. Min Act: -0.1700
Data Index: 7666545 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7034. Min Act: -0.1700
Data Index: 457199 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7034. Min Act: -0.1700
Data Index: 1804447 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.7034. Min Act: -0.1700
Data Index: 640865 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6722. Min Act: -0.1700
Data Index: 6475204 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 4562159 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 640869 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 7364226 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 6540965 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 8196569 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 3568180 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6409. Min Act: -0.1700
Data Index: 6054315 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8911. Min Range: -3.8911
Max Act: 3.6096. Min Act: -0.1700
Data Index: 4024727 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19