Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.9567. Min Act: -0.1700
Data Index: 998062 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.7380. Min Act: -0.1700
Data Index: 127990 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.7067. Min Act: -0.1700
Data Index: 5405443 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.6755. Min Act: -0.1700
Data Index: 7888705 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.6130. Min Act: -0.1700
Data Index: 3878723 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5505. Min Act: -0.1700
Data Index: 940406 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5505. Min Act: -0.1700
Data Index: 6062233 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5505. Min Act: -0.1700
Data Index: 503427 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.5192. Min Act: -0.1700
Data Index: 3653773 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4880. Min Act: -0.1700
Data Index: 5058469 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4567. Min Act: -0.1700
Data Index: 1681324 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4567. Min Act: -0.1700
Data Index: 7662320 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4567. Min Act: -0.1700
Data Index: 2862992 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4567. Min Act: -0.1700
Data Index: 7436171 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4255. Min Act: -0.1700
Data Index: 6852604 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4255. Min Act: -0.1700
Data Index: 2821891 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.4255. Min Act: -0.1700
Data Index: 4135811 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.3630. Min Act: -0.1700
Data Index: 5889340 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.3942. Min Act: -0.1700
Data Index: 6506654 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9567. Min Range: -5.9567
Max Act: 5.3942. Min Act: -0.1700
Data Index: 1103306 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19