Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5113 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.5456. Min Act: -0.1694
Data Index: 7575986 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.4518. Min Act: -0.1669
Data Index: 1453246 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.4206. Min Act: -0.1700
Data Index: 7119986 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3893. Min Act: -0.1694
Data Index: 2401617 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3581. Min Act: -0.1699
Data Index: 3856315 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3268. Min Act: -0.1668
Data Index: 6161518 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3581. Min Act: -0.1691
Data Index: 7002350 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3581. Min Act: -0.1695
Data Index: 840206 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3268. Min Act: -0.1682
Data Index: 8611686 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3581. Min Act: -0.1693
Data Index: 6026944 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3268. Min Act: -0.1686
Data Index: 4201280 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.3268. Min Act: -0.1700
Data Index: 4363325 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2956. Min Act: -0.1698
Data Index: 7051724 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2956. Min Act: -0.1686
Data Index: 7505457 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2643. Min Act: -0.1700
Data Index: 4037327 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2956. Min Act: -0.1700
Data Index: 4204041 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2956. Min Act: -0.1700
Data Index: 7017816 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2956. Min Act: -0.1699
Data Index: 8769983 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2643. Min Act: -0.1682
Data Index: 6482764 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5456. Min Range: -6.5456
Max Act: 6.2643. Min Act: -0.1698
Data Index: 3940017 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19