Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.4826. Min Act: -0.1414
Data Index: 264110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.4514. Min Act: -0.1694
Data Index: 1534549 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3264. Min Act: -0.1698
Data Index: 70250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2951. Min Act: -0.1382
Data Index: 6626201 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2639. Min Act: -0.1699
Data Index: 4818636 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2014. Min Act: -0.1686
Data Index: 2425725 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.1076. Min Act: -0.1599
Data Index: 2869242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.0451. Min Act: -0.1623
Data Index: 7590767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.0139. Min Act: -0.1677
Data Index: 6803539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.9826. Min Act: -0.1628
Data Index: 4970271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.9826. Min Act: -0.1688
Data Index: 603498 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.9826. Min Act: -0.1382
Data Index: 3263083 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.9201. Min Act: -0.1686
Data Index: 8750821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.8889. Min Act: -0.1700
Data Index: 2010816 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.8576. Min Act: -0.1628
Data Index: 7360438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.8576. Min Act: -0.1382
Data Index: 1759005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.8576. Min Act: -0.1382
Data Index: 2607743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.8576. Min Act: -0.1382
Data Index: 7903763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.8264. Min Act: -0.1587
Data Index: 3779036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4826. Min Range: -5.4826
Max Act: 4.7951. Min Act: -0.1700
Data Index: 7117448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19