Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.6704. Min Act: -0.1700
Data Index: 6704844 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.5142. Min Act: -0.1700
Data Index: 5780697 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.4829. Min Act: -0.1700
Data Index: 7259748 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.4517. Min Act: -0.1700
Data Index: 261346 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.3892. Min Act: -0.1700
Data Index: 7084843 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1276970 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.3579. Min Act: -0.1700
Data Index: 6704852 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.3892. Min Act: -0.1700
Data Index: 204450 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2642. Min Act: -0.1700
Data Index: 6693673 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2642. Min Act: -0.1700
Data Index: 4630565 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2642. Min Act: -0.1700
Data Index: 6704840 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2329. Min Act: -0.1700
Data Index: 1276963 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2329. Min Act: -0.1700
Data Index: 1182607 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2329. Min Act: -0.1700
Data Index: 6704841 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2329. Min Act: -0.1700
Data Index: 1276969 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2329. Min Act: -0.1700
Data Index: 4082176 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.1704. Min Act: -0.1700
Data Index: 8683663 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.2017. Min Act: -0.1700
Data Index: 6958821 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.1704. Min Act: -0.1700
Data Index: 3262658 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6704. Min Range: -5.6704
Max Act: 5.1392. Min Act: -0.1700
Data Index: 4939509 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19