Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.3492. Min Act: -0.1700
Data Index: 4165848 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.1617. Min Act: -0.1700
Data Index: 2429224 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.0992. Min Act: -0.1700
Data Index: 1591457 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.1304. Min Act: -0.1700
Data Index: 744065 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.1304. Min Act: -0.1700
Data Index: 2269457 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.1304. Min Act: -0.1700
Data Index: 7354191 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.0992. Min Act: -0.1700
Data Index: 5791453 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3492. Min Range: -5.3492
Max Act: 5.0054. Min Act: -0.1700
Data Index: 8407976 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9742. Min Act: -0.1700
Data Index: 6443011 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9429. Min Act: -0.1700
Data Index: 3481036 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9429. Min Act: -0.1700
Data Index: 604189 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9117. Min Act: -0.1700
Data Index: 6381978 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9117. Min Act: -0.1700
Data Index: 5974459 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9117. Min Act: -0.1700
Data Index: 731975 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9429. Min Act: -0.1700
Data Index: 4975197 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.8804. Min Act: -0.1700
Data Index: 6956893 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9429. Min Act: -0.1700
Data Index: 483849 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.7554. Min Act: -0.1700
Data Index: 6550812 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9117. Min Act: -0.1700
Data Index: 5571097 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3492. Min Range: -5.3492
Max Act: 4.9117. Min Act: -0.1700
Data Index: 4803777 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19