Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.2910. Min Act: -0.1700
Data Index: 8806881 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.2910. Min Act: -0.1700
Data Index: 5184654 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.2597. Min Act: -0.1700
Data Index: 3221396 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.2285. Min Act: -0.1700
Data Index: 3561061 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1972. Min Act: -0.1700
Data Index: 2322996 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1972. Min Act: -0.1700
Data Index: 2728173 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1972. Min Act: -0.1700
Data Index: 755964 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1347. Min Act: -0.1700
Data Index: 7690201 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1347. Min Act: -0.1700
Data Index: 6849832 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1347. Min Act: -0.1700
Data Index: 2833539 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1347. Min Act: -0.1700
Data Index: 2456845 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.1347. Min Act: -0.1700
Data Index: 1933687 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.0722. Min Act: -0.1700
Data Index: 6914876 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.0410. Min Act: -0.1700
Data Index: 1477018 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2910. Min Range: -7.2910
Max Act: 7.0410. Min Act: -0.1700
Data Index: 971911 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.9785. Min Act: -0.1700
Data Index: 6763817 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.9785. Min Act: -0.1700
Data Index: 5184177 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.9785. Min Act: -0.1700
Data Index: 8320300 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.9472. Min Act: -0.1700
Data Index: 2453089 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2910. Min Range: -7.2910
Max Act: 6.9472. Min Act: -0.1700
Data Index: 2506400 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19