Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5913 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.2776. Min Act: -0.1700
Data Index: 1333745 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.2463. Min Act: -0.1700
Data Index: 4140047 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.2776. Min Act: -0.1700
Data Index: 7190123 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.2151. Min Act: -0.1700
Data Index: 11998 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.1213. Min Act: -0.1700
Data Index: 7492744 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.1213. Min Act: -0.1700
Data Index: 4520093 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0901. Min Act: -0.1700
Data Index: 7327580 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0588. Min Act: -0.1700
Data Index: 1539501 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0588. Min Act: -0.1700
Data Index: 4903782 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0588. Min Act: -0.1700
Data Index: 5207108 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0588. Min Act: -0.1700
Data Index: 6345409 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0276. Min Act: -0.1700
Data Index: 4811553 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0276. Min Act: -0.1700
Data Index: 5755226 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0276. Min Act: -0.1700
Data Index: 4401396 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0588. Min Act: -0.1700
Data Index: 2661938 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2776. Min Range: -5.2776
Max Act: 5.0276. Min Act: -0.1700
Data Index: 4762014 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2776. Min Range: -5.2776
Max Act: 4.9963. Min Act: -0.1700
Data Index: 8486390 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2776. Min Range: -5.2776
Max Act: 4.9651. Min Act: -0.1700
Data Index: 2068417 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2776. Min Range: -5.2776
Max Act: 4.9963. Min Act: -0.1700
Data Index: 5953700 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2776. Min Range: -5.2776
Max Act: 4.9651. Min Act: -0.1700
Data Index: 1305053 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19