Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2436. Min Range: -6.2436
Max Act: 6.2436. Min Act: -0.1700
Data Index: 2663640 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2436. Min Range: -6.2436
Max Act: 6.2124. Min Act: -0.1700
Data Index: 5513539 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2436. Min Range: -6.2436
Max Act: 6.1186. Min Act: -0.1700
Data Index: 6940130 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2436. Min Range: -6.2436
Max Act: 6.0561. Min Act: -0.1700
Data Index: 3360554 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.8999. Min Act: -0.1700
Data Index: 6940136 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.8686. Min Act: -0.1700
Data Index: 7516573 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.8374. Min Act: -0.1700
Data Index: 7090608 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.8061. Min Act: -0.1700
Data Index: 6538523 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.7749. Min Act: -0.1700
Data Index: 3534579 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.7436. Min Act: -0.1700
Data Index: 1002708 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.7436. Min Act: -0.1700
Data Index: 8405647 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.7124. Min Act: -0.1700
Data Index: 364330 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.7124. Min Act: -0.1700
Data Index: 3050090 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.7124. Min Act: -0.1700
Data Index: 2932664 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.6811. Min Act: -0.1700
Data Index: 3842875 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.6811. Min Act: -0.1700
Data Index: 3421786 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.6811. Min Act: -0.1700
Data Index: 4937894 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.6186. Min Act: -0.1700
Data Index: 7470003 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.6499. Min Act: -0.1700
Data Index: 720228 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2436. Min Range: -6.2436
Max Act: 5.6499. Min Act: -0.1700
Data Index: 4087805 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19