Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.7429. Min Act: -0.1700
Data Index: 755287 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.6179. Min Act: -0.1700
Data Index: 97987 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.6492. Min Act: -0.1700
Data Index: 2305079 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.5554. Min Act: -0.1700
Data Index: 7789116 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.5554. Min Act: -0.1700
Data Index: 2318171 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.3992. Min Act: -0.1700
Data Index: 8362011 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.3679. Min Act: -0.1700
Data Index: 8052116 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.3679. Min Act: -0.1700
Data Index: 7798866 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2741. Min Act: -0.1700
Data Index: 951837 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2741. Min Act: -0.1700
Data Index: 7231899 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2116. Min Act: -0.1700
Data Index: 5345510 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2429. Min Act: -0.1700
Data Index: 8786728 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2116. Min Act: -0.1700
Data Index: 2672837 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2116. Min Act: -0.1700
Data Index: 1790560 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2116. Min Act: -0.1700
Data Index: 2672835 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2116. Min Act: -0.1700
Data Index: 1393176 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.1804. Min Act: -0.1700
Data Index: 2672826 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2116. Min Act: -0.1700
Data Index: 2672836 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.2116. Min Act: -0.1700
Data Index: 575680 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7429. Min Range: -4.7429
Max Act: 4.1804. Min Act: -0.1700
Data Index: 2672827 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19