Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.3421. Min Act: -0.1700
Data Index: 4803646 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.2171. Min Act: -0.1700
Data Index: 1323106 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.1859. Min Act: -0.1700
Data Index: 6429219 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.1546. Min Act: -0.1700
Data Index: 1879052 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.1234. Min Act: -0.1700
Data Index: 6472046 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.0921. Min Act: -0.1700
Data Index: 407052 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.0609. Min Act: -0.1700
Data Index: 4605246 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.0609. Min Act: -0.1700
Data Index: 327066 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.0296. Min Act: -0.1700
Data Index: 5564682 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.0296. Min Act: -0.1700
Data Index: 3770038 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3421. Min Range: -5.3421
Max Act: 5.0296. Min Act: -0.1700
Data Index: 4496203 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9671. Min Act: -0.1700
Data Index: 3220445 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9671. Min Act: -0.1700
Data Index: 3974486 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9046. Min Act: -0.1700
Data Index: 6267857 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9046. Min Act: -0.1700
Data Index: 1700127 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9046. Min Act: -0.1700
Data Index: 147791 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9046. Min Act: -0.1700
Data Index: 2946310 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9046. Min Act: -0.1700
Data Index: 6522124 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.8734. Min Act: -0.1700
Data Index: 7021054 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3421. Min Range: -5.3421
Max Act: 4.9046. Min Act: -0.1700
Data Index: 1985928 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19