Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 780 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.7331. Min Act: -0.1678
Data Index: 7647134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.7331. Min Act: -0.1700
Data Index: 7644193 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.7085. Min Act: -0.1691
Data Index: 5278312 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1700
Data Index: 3199312 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1698
Data Index: 4452672 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6357. Min Act: -0.1688
Data Index: 2814464 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1698
Data Index: 4228037 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1684
Data Index: 2264377 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1699
Data Index: 5334042 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1700
Data Index: 2005392 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1695
Data Index: 1932049 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1696
Data Index: 1864068 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1692
Data Index: 1602551 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1691
Data Index: 1592407 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1700
Data Index: 3905380 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1686
Data Index: 1111418 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1698
Data Index: 5483197 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1690
Data Index: 947555 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6277. Min Act: -0.1681
Data Index: 5483844 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7331. Min Range: -0.7331
Max Act: 0.6198. Min Act: -0.1700
Data Index: 617329 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19