Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.4017. Min Act: -0.1700
Data Index: 8740912 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.3390. Min Act: -0.1700
Data Index: 2984069 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.3076. Min Act: -0.1700
Data Index: 3763815 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.2448. Min Act: -0.1700
Data Index: 2188076 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1819. Min Act: -0.1700
Data Index: 6075760 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1976. Min Act: -0.1700
Data Index: 2030252 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1976. Min Act: -0.1700
Data Index: 8408256 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1976. Min Act: -0.1700
Data Index: 4609544 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1662. Min Act: -0.1700
Data Index: 1629727 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1662. Min Act: -0.1700
Data Index: 8306632 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1347. Min Act: -0.1700
Data Index: 8324123 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1504. Min Act: -0.1700
Data Index: 1277095 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1347. Min Act: -0.1700
Data Index: 5201398 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1347. Min Act: -0.1700
Data Index: 7384702 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1347. Min Act: -0.1700
Data Index: 3004122 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1189. Min Act: -0.1700
Data Index: 6062031 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1189. Min Act: -0.1700
Data Index: 4579113 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1189. Min Act: -0.1700
Data Index: 1711606 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1032. Min Act: -0.1700
Data Index: 5223300 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4017. Min Range: -3.4017
Max Act: 3.1032. Min Act: -0.1700
Data Index: 5567481 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19