Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3932 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 3749648 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4687. Min Act: -0.1700
Data Index: 6978404 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 4389616 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4687. Min Act: -0.1700
Data Index: 7661062 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 3905199 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4062. Min Act: -0.1700
Data Index: 5973552 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 626817 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 6984374 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 3153749 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 6135730 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 6063005 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 7109019 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 1370469 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 2231634 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 122184 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 2776683 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3125. Min Act: -0.1700
Data Index: 5757841 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 4993972 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3125. Min Act: -0.1700
Data Index: 62363 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3125. Min Act: -0.1700
Data Index: 6418994 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19