Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.7516. Min Act: -0.1700
Data Index: 1700185 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.4391. Min Act: -0.1700
Data Index: 1700173 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.3453. Min Act: -0.1700
Data Index: 5198508 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.2828. Min Act: -0.1700
Data Index: 5297217 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.3141. Min Act: -0.1700
Data Index: 3189463 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.2516. Min Act: -0.1700
Data Index: 1700183 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.3141. Min Act: -0.1700
Data Index: 5962682 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.2203. Min Act: -0.1700
Data Index: 6379004 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.2203. Min Act: -0.1700
Data Index: 1089797 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.1891. Min Act: -0.1700
Data Index: 2656496 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.1891. Min Act: -0.1700
Data Index: 1700177 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.1891. Min Act: -0.1700
Data Index: 738318 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.0953. Min Act: -0.1700
Data Index: 5856764 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.1266. Min Act: -0.1700
Data Index: 780429 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.1578. Min Act: -0.1700
Data Index: 6867269 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.0953. Min Act: -0.1700
Data Index: 1700184 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.0641. Min Act: -0.1700
Data Index: 384426 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.0953. Min Act: -0.1700
Data Index: 5454694 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.0641. Min Act: -0.1700
Data Index: 1700182 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7516. Min Range: -6.7516
Max Act: 6.0328. Min Act: -0.1700
Data Index: 1700181 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19