Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1358. Min Range: -4.1358
Max Act: 4.1358. Min Act: -0.1700
Data Index: 4147797 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1358. Min Range: -4.1358
Max Act: 4.1045. Min Act: -0.1700
Data Index: 5153613 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1358. Min Range: -4.1358
Max Act: 4.0420. Min Act: -0.1700
Data Index: 2362927 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9482. Min Act: -0.1700
Data Index: 6387423 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9482. Min Act: -0.1700
Data Index: 1776872 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9795. Min Act: -0.1700
Data Index: 3168842 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9795. Min Act: -0.1700
Data Index: 357738 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9482. Min Act: -0.1700
Data Index: 1558355 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9795. Min Act: -0.1700
Data Index: 350233 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9170. Min Act: -0.1700
Data Index: 5244877 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9482. Min Act: -0.1700
Data Index: 1680167 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9013. Min Act: -0.1700
Data Index: 1405998 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9170. Min Act: -0.1700
Data Index: 2475889 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9170. Min Act: -0.1700
Data Index: 6493042 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9170. Min Act: -0.1700
Data Index: 3194495 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9013. Min Act: -0.1700
Data Index: 1627780 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9013. Min Act: -0.1700
Data Index: 6814919 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.8857. Min Act: -0.1700
Data Index: 6752354 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9170. Min Act: -0.1700
Data Index: 4339514 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1358. Min Range: -4.1358
Max Act: 3.9013. Min Act: -0.1700
Data Index: 4587350 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19