Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 300 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.5474. Min Act: -0.1700
Data Index: 3134387 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.3287. Min Act: -0.1700
Data Index: 3464913 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.1724. Min Act: -0.1700
Data Index: 6853209 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.1412. Min Act: -0.1700
Data Index: 8516451 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.1412. Min Act: -0.1700
Data Index: 2647104 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.1412. Min Act: -0.1700
Data Index: 1838403 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.1099. Min Act: -0.1700
Data Index: 3653586 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.1099. Min Act: -0.1700
Data Index: 150627 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.1412. Min Act: -0.1700
Data Index: 4234004 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0787. Min Act: -0.1700
Data Index: 8139009 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0787. Min Act: -0.1700
Data Index: 3111429 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0787. Min Act: -0.1700
Data Index: 7583259 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0162. Min Act: -0.1700
Data Index: 7651480 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0474. Min Act: -0.1700
Data Index: 1867862 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0474. Min Act: -0.1700
Data Index: 3363472 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0162. Min Act: -0.1700
Data Index: 367645 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0162. Min Act: -0.1700
Data Index: 5569931 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5474. Min Range: -5.5474
Max Act: 5.0162. Min Act: -0.1700
Data Index: 5149565 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5474. Min Range: -5.5474
Max Act: 4.9849. Min Act: -0.1700
Data Index: 516436 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5474. Min Range: -5.5474
Max Act: 4.9849. Min Act: -0.1700
Data Index: 873444 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19