Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3214. Min Range: -6.3214
Max Act: 6.3214. Min Act: -0.1700
Data Index: 7002824 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3214. Min Range: -6.3214
Max Act: 6.1339. Min Act: -0.1700
Data Index: 1084317 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.9464. Min Act: -0.1700
Data Index: 139558 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.8526. Min Act: -0.1700
Data Index: 2926018 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.8839. Min Act: -0.1700
Data Index: 4400838 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.8526. Min Act: -0.1700
Data Index: 785278 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.8214. Min Act: -0.1700
Data Index: 3481168 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.8214. Min Act: -0.1700
Data Index: 1890388 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.7589. Min Act: -0.1700
Data Index: 1204751 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6723571 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.7276. Min Act: -0.1700
Data Index: 3742134 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.7276. Min Act: -0.1700
Data Index: 1116523 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6964. Min Act: -0.1700
Data Index: 3240608 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6651. Min Act: -0.1700
Data Index: 2872047 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6651. Min Act: -0.1700
Data Index: 2786875 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6339. Min Act: -0.1700
Data Index: 876724 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6339. Min Act: -0.1700
Data Index: 6619614 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6339. Min Act: -0.1700
Data Index: 6671380 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6339. Min Act: -0.1700
Data Index: 5416466 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3214. Min Range: -6.3214
Max Act: 5.6339. Min Act: -0.1700
Data Index: 1403667 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19