Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1368 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.3880. Min Act: -0.1700
Data Index: 8739478 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.3704. Min Act: -0.1700
Data Index: 2206861 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.3439. Min Act: -0.1700
Data Index: 3417977 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.3351. Min Act: -0.1700
Data Index: 7029951 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2910. Min Act: -0.1700
Data Index: 6335987 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2910. Min Act: -0.1700
Data Index: 1604684 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2557. Min Act: -0.1700
Data Index: 4213804 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2381. Min Act: -0.1700
Data Index: 3163466 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2381. Min Act: -0.1700
Data Index: 1804854 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2293. Min Act: -0.1700
Data Index: 6540683 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2205. Min Act: -0.1700
Data Index: 301194 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2029. Min Act: -0.1700
Data Index: 6551159 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2029. Min Act: -0.1699
Data Index: 5692737 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2029. Min Act: -0.1700
Data Index: 7580573 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.1853. Min Act: -0.1700
Data Index: 862533 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.1853. Min Act: -0.1700
Data Index: 6315634 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.1941. Min Act: -0.1700
Data Index: 6897447 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.2029. Min Act: -0.1700
Data Index: 6716172 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.1765. Min Act: -0.1700
Data Index: 5999616 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3880. Min Range: -1.3880
Max Act: 1.1853. Min Act: -0.1700
Data Index: 1383015 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19