Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1835 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0900. Min Range: -3.0900
Max Act: 3.0900. Min Act: -0.1463
Data Index: 2779572 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0900. Min Range: -3.0900
Max Act: 3.0426. Min Act: -0.1611
Data Index: 2180106 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0900. Min Range: -3.0900
Max Act: 3.0269. Min Act: -0.1692
Data Index: 3900940 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0900. Min Range: -3.0900
Max Act: 3.0111. Min Act: -0.1700
Data Index: 6922945 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9636. Min Act: -0.1700
Data Index: 2180105 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9478. Min Act: -0.1686
Data Index: 1097759 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9478. Min Act: -0.1632
Data Index: 1097760 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9320. Min Act: -0.1670
Data Index: 2859979 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9320. Min Act: -0.1689
Data Index: 8553080 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9320. Min Act: -0.1700
Data Index: 897152 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9003. Min Act: -0.1700
Data Index: 6052662 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9003. Min Act: -0.1697
Data Index: 746939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8844. Min Act: -0.1651
Data Index: 8420346 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9003. Min Act: -0.1697
Data Index: 746947 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9003. Min Act: -0.1697
Data Index: 746931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9003. Min Act: -0.1700
Data Index: 709678 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9161. Min Act: -0.1699
Data Index: 3674044 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8844. Min Act: -0.1698
Data Index: 746940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9003. Min Act: -0.1699
Data Index: 4460872 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8844. Min Act: -0.1698
Data Index: 746948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19