Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.5305. Min Act: -0.1700
Data Index: 4507249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.5305. Min Act: -0.1700
Data Index: 7183552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 5118915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4680. Min Act: -0.1700
Data Index: 3941467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 338683 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 3024512 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 3317496 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 8471434 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 1293804 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 3224304 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 5751651 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 805820 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 2732901 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 8295713 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 440664 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 1086710 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 3095246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3742. Min Act: -0.1700
Data Index: 4355725 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.4055. Min Act: -0.1700
Data Index: 5370561 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5305. Min Range: -4.5305
Max Act: 4.3430. Min Act: -0.1700
Data Index: 22818 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19