Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2473 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.4758. Min Act: -0.1700
Data Index: 2391166 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.4758. Min Act: -0.1700
Data Index: 5843964 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.4446. Min Act: -0.1700
Data Index: 8188773 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.2571. Min Act: -0.1700
Data Index: 1351096 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.1946. Min Act: -0.1700
Data Index: 5816259 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.2258. Min Act: -0.1700
Data Index: 5999078 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.1946. Min Act: -0.1700
Data Index: 1822450 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.1633. Min Act: -0.1700
Data Index: 4765302 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.2258. Min Act: -0.1700
Data Index: 4241026 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.1946. Min Act: -0.1700
Data Index: 3834219 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.1633. Min Act: -0.1700
Data Index: 6419786 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.1633. Min Act: -0.1700
Data Index: 7810198 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.1321. Min Act: -0.1700
Data Index: 3468756 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.0383. Min Act: -0.1700
Data Index: 2308724 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.0383. Min Act: -0.1700
Data Index: 1071500 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.0071. Min Act: -0.1700
Data Index: 3626334 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.0071. Min Act: -0.1700
Data Index: 6483030 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4758. Min Range: -7.4758
Max Act: 7.0071. Min Act: -0.1700
Data Index: 5814899 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4758. Min Range: -7.4758
Max Act: 6.9758. Min Act: -0.1700
Data Index: 7397317 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4758. Min Range: -7.4758
Max Act: 6.9446. Min Act: -0.1700
Data Index: 6265502 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19