Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.8412. Min Act: -0.1700
Data Index: 3672780 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.8099. Min Act: -0.1700
Data Index: 1892963 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7787. Min Act: -0.1700
Data Index: 472994 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7787. Min Act: -0.1700
Data Index: 7927224 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7787. Min Act: -0.1700
Data Index: 6050259 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7161. Min Act: -0.1700
Data Index: 4318299 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7474. Min Act: -0.1700
Data Index: 6183392 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7161. Min Act: -0.1700
Data Index: 4444295 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7161. Min Act: -0.1700
Data Index: 519572 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7161. Min Act: -0.1700
Data Index: 5014998 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.7161. Min Act: -0.1700
Data Index: 7557604 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6848. Min Act: -0.1700
Data Index: 5841401 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6848. Min Act: -0.1700
Data Index: 4472083 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6848. Min Act: -0.1700
Data Index: 4351086 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6535. Min Act: -0.1700
Data Index: 1214147 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6535. Min Act: -0.1700
Data Index: 8079052 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6535. Min Act: -0.1700
Data Index: 2022231 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6535. Min Act: -0.1700
Data Index: 212807 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6535. Min Act: -0.1700
Data Index: 86554 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8412. Min Range: -3.8412
Max Act: 3.6222. Min Act: -0.1700
Data Index: 7317350 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19