Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5032 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.2887. Min Act: -0.1700
Data Index: 393129 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.2574. Min Act: -0.1700
Data Index: 2551272 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.2262. Min Act: -0.1698
Data Index: 5086534 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.2262. Min Act: -0.1651
Data Index: 2063579 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.2262. Min Act: -0.1700
Data Index: 2445883 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1949. Min Act: -0.1700
Data Index: 4728031 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1697
Data Index: 4542372 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1699
Data Index: 2548700 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1700
Data Index: 2929778 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1700
Data Index: 1384107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1700
Data Index: 6719298 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1700
Data Index: 3516466 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1700
Data Index: 5796953 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1700
Data Index: 847381 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1637. Min Act: -0.1700
Data Index: 5364750 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1324. Min Act: -0.1700
Data Index: 1546640 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1324. Min Act: -0.1700
Data Index: 1727643 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1324. Min Act: -0.1700
Data Index: 2024511 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1324. Min Act: -0.1700
Data Index: 3958609 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2887. Min Range: -4.2887
Max Act: 4.1324. Min Act: -0.1697
Data Index: 4402846 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19