Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2080 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.9488. Min Act: -0.1694
Data Index: 2322421 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.9800. Min Act: -0.1700
Data Index: 6994275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.9175. Min Act: -0.1700
Data Index: 4183865 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1700
Data Index: 6729140 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1700
Data Index: 2881629 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1700
Data Index: 6729152 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1695
Data Index: 7295175 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1700
Data Index: 4639362 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1700
Data Index: 6220023 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1699
Data Index: 6561559 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8550. Min Act: -0.1700
Data Index: 4183866 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.7612. Min Act: -0.1700
Data Index: 6277875 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.8237. Min Act: -0.1700
Data Index: 3917211 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.7924. Min Act: -0.1700
Data Index: 2557560 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.7612. Min Act: -0.1700
Data Index: 1644375 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.7612. Min Act: -0.1700
Data Index: 2659222 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.7612. Min Act: -0.1700
Data Index: 8525570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.7299. Min Act: -0.1700
Data Index: 3588158 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.6986. Min Act: -0.1700
Data Index: 5551894 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9800. Min Range: -3.9800
Max Act: 3.7299. Min Act: -0.1700
Data Index: 6774167 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19