Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1578. Min Range: -5.1578
Max Act: 5.1578. Min Act: -0.1700
Data Index: 7820255 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1578. Min Range: -5.1578
Max Act: 5.0953. Min Act: -0.1700
Data Index: 1244198 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1578. Min Range: -5.1578
Max Act: 5.0015. Min Act: -0.1700
Data Index: 6691602 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1578. Min Range: -5.1578
Max Act: 5.0015. Min Act: -0.1700
Data Index: 7584267 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.9390. Min Act: -0.1700
Data Index: 3875007 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.9703. Min Act: -0.1700
Data Index: 3997977 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.9703. Min Act: -0.1700
Data Index: 5380737 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.9703. Min Act: -0.1700
Data Index: 932937 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.9078. Min Act: -0.1700
Data Index: 8187260 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.9390. Min Act: -0.1700
Data Index: 8591200 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8765. Min Act: -0.1700
Data Index: 5221234 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8765. Min Act: -0.1700
Data Index: 6640144 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8765. Min Act: -0.1700
Data Index: 8036251 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2112995 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8453. Min Act: -0.1700
Data Index: 8645339 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8453. Min Act: -0.1700
Data Index: 7840738 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8140. Min Act: -0.1700
Data Index: 4395952 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.8140. Min Act: -0.1700
Data Index: 6060322 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.7515. Min Act: -0.1700
Data Index: 276269 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1578. Min Range: -5.1578
Max Act: 4.7828. Min Act: -0.1700
Data Index: 6609530 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19