Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3839 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.3839. Min Act: -0.1700
Data Index: 5995958 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.3214. Min Act: -0.1700
Data Index: 4840796 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2902. Min Act: -0.1700
Data Index: 4114405 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2589. Min Act: -0.1700
Data Index: 1179347 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2589. Min Act: -0.1700
Data Index: 4723150 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2589. Min Act: -0.1700
Data Index: 2592577 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2589. Min Act: -0.1700
Data Index: 7006621 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2277. Min Act: -0.1700
Data Index: 4114407 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2277. Min Act: -0.1700
Data Index: 603373 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1964. Min Act: -0.1700
Data Index: 2592574 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.2277. Min Act: -0.1700
Data Index: 3976612 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1964. Min Act: -0.1700
Data Index: 1005210 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1964. Min Act: -0.1700
Data Index: 6809457 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1652. Min Act: -0.1700
Data Index: 5917720 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1652. Min Act: -0.1700
Data Index: 753280 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1652. Min Act: -0.1700
Data Index: 4114406 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1652. Min Act: -0.1700
Data Index: 2985165 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1652. Min Act: -0.1700
Data Index: 1737651 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1964. Min Act: -0.1700
Data Index: 3317963 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3839. Min Range: -5.3839
Max Act: 5.1652. Min Act: -0.1700
Data Index: 1898983 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19