Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5877. Min Act: -0.1699
Data Index: 3611041 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5877. Min Act: -0.1699
Data Index: 927756 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4580218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5252. Min Act: -0.1700
Data Index: 2657612 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4627. Min Act: -0.1692
Data Index: 8240738 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4940. Min Act: -0.1700
Data Index: 1626944 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4627. Min Act: -0.1700
Data Index: 601287 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4627. Min Act: -0.1700
Data Index: 2636533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4315. Min Act: -0.1700
Data Index: 1079879 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4315. Min Act: -0.1700
Data Index: 6111362 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4315. Min Act: -0.1700
Data Index: 8744533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4315. Min Act: -0.1700
Data Index: 8034840 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4002. Min Act: -0.1700
Data Index: 7571895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4002. Min Act: -0.1700
Data Index: 612271 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4002. Min Act: -0.1700
Data Index: 8744408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3690. Min Act: -0.1698
Data Index: 7067449 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3690. Min Act: -0.1700
Data Index: 7511051 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3690. Min Act: -0.1700
Data Index: 6948540 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3690. Min Act: -0.1693
Data Index: 2745429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3690. Min Act: -0.1700
Data Index: 7581976 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19