Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4959 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.9700. Min Act: -0.1700
Data Index: 4152725 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.9700. Min Act: -0.1700
Data Index: 4665113 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.9075. Min Act: -0.1700
Data Index: 4195662 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.7825. Min Act: -0.1700
Data Index: 1397335 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.7825. Min Act: -0.1700
Data Index: 7912568 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.7200. Min Act: -0.1700
Data Index: 6128496 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.6575. Min Act: -0.1700
Data Index: 8147037 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5950. Min Act: -0.1700
Data Index: 7992680 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5950. Min Act: -0.1700
Data Index: 6634701 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5950. Min Act: -0.1700
Data Index: 3532374 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 1843389 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 7846757 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 7059517 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 3571571 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 6853160 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 4268077 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 1944481 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.5325. Min Act: -0.1700
Data Index: 8223614 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.4700. Min Act: -0.1700
Data Index: 1761706 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9700. Min Range: -8.9700
Max Act: 8.4700. Min Act: -0.1700
Data Index: 3837103 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19