Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8732. Min Act: -0.1700
Data Index: 2070835 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8817. Min Act: -0.1700
Data Index: 1172392 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8475. Min Act: -0.1700
Data Index: 4100398 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8389. Min Act: -0.1700
Data Index: 5295728 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8218. Min Act: -0.1700
Data Index: 1566019 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8132. Min Act: -0.1700
Data Index: 7185139 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8218. Min Act: -0.1700
Data Index: 6750464 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8046. Min Act: -0.1700
Data Index: 8280586 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8132. Min Act: -0.1700
Data Index: 3845599 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8132. Min Act: -0.1700
Data Index: 6076919 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8132. Min Act: -0.1700
Data Index: 3076965 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8132. Min Act: -0.1700
Data Index: 7704735 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.8132. Min Act: -0.1700
Data Index: 2769210 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.7960. Min Act: -0.1700
Data Index: 8117190 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.7788. Min Act: -0.1700
Data Index: 6673012 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.7788. Min Act: -0.1700
Data Index: 79696 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.7874. Min Act: -0.1700
Data Index: 8717707 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.7788. Min Act: -0.1700
Data Index: 6345416 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.7788. Min Act: -0.1700
Data Index: 7335666 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8817. Min Range: -1.8817
Max Act: 1.7788. Min Act: -0.1700
Data Index: 6565697 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19