Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 517 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.2209. Min Act: -0.1700
Data Index: 2195069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.2033. Min Act: -0.1700
Data Index: 7235302 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1857. Min Act: -0.1700
Data Index: 2295869 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1769. Min Act: -0.1700
Data Index: 1353293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1769. Min Act: -0.1700
Data Index: 4345165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1681. Min Act: -0.1700
Data Index: 1364568 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1681. Min Act: -0.1700
Data Index: 2555396 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1593. Min Act: -0.1700
Data Index: 2546687 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1769. Min Act: -0.1700
Data Index: 4600083 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1593. Min Act: -0.1700
Data Index: 6134197 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1417. Min Act: -0.1700
Data Index: 4806642 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1681. Min Act: -0.1700
Data Index: 4815472 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1593. Min Act: -0.1700
Data Index: 7691753 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1505. Min Act: -0.1700
Data Index: 7426127 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1417. Min Act: -0.1700
Data Index: 3758781 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1505. Min Act: -0.1700
Data Index: 6478326 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1417. Min Act: -0.1700
Data Index: 6711554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1329. Min Act: -0.1700
Data Index: 2961910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1505. Min Act: -0.1700
Data Index: 1570508 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2209. Min Range: -1.2209
Max Act: 1.1329. Min Act: -0.1700
Data Index: 6223116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19