Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.5831. Min Act: -0.1700
Data Index: 291923 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.5831. Min Act: -0.1700
Data Index: 4087518 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.5206. Min Act: -0.1700
Data Index: 7608887 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.4269. Min Act: -0.1700
Data Index: 6159257 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3956. Min Act: -0.1700
Data Index: 1746949 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3956. Min Act: -0.1700
Data Index: 7123473 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3956. Min Act: -0.1700
Data Index: 4938618 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3956. Min Act: -0.1700
Data Index: 2732075 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3644. Min Act: -0.1700
Data Index: 833062 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3644. Min Act: -0.1700
Data Index: 5056198 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3331. Min Act: -0.1700
Data Index: 5368779 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3331. Min Act: -0.1700
Data Index: 3243946 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3019. Min Act: -0.1700
Data Index: 481811 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.3019. Min Act: -0.1700
Data Index: 1311375 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.2706. Min Act: -0.1700
Data Index: 7950459 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.2706. Min Act: -0.1700
Data Index: 813577 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.2706. Min Act: -0.1700
Data Index: 8749600 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.2706. Min Act: -0.1700
Data Index: 1871028 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.2393. Min Act: -0.1700
Data Index: 3692213 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5831. Min Range: -4.5831
Max Act: 4.2393. Min Act: -0.1700
Data Index: 1532971 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19