Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4233 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0265. Min Range: -4.0265
Max Act: 4.0265. Min Act: -0.1700
Data Index: 3791677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8702. Min Act: -0.1700
Data Index: 7993343 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8389. Min Act: -0.1700
Data Index: 1671351 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8077. Min Act: -0.1700
Data Index: 338617 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8077. Min Act: -0.1700
Data Index: 907942 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8077. Min Act: -0.1700
Data Index: 7993342 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8077. Min Act: -0.1700
Data Index: 5286928 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8389. Min Act: -0.1700
Data Index: 1892855 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.8077. Min Act: -0.1700
Data Index: 8397105 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.7451. Min Act: -0.1700
Data Index: 3787775 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.7451. Min Act: -0.1700
Data Index: 813936 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.7451. Min Act: -0.1700
Data Index: 17413 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.7138. Min Act: -0.1700
Data Index: 5003253 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.7138. Min Act: -0.1700
Data Index: 6024099 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.7138. Min Act: -0.1700
Data Index: 958328 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.6825. Min Act: -0.1700
Data Index: 7438789 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.6512. Min Act: -0.1700
Data Index: 4360664 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.6825. Min Act: -0.1700
Data Index: 5605074 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.6512. Min Act: -0.1700
Data Index: 907944 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0265. Min Range: -4.0265
Max Act: 3.6199. Min Act: -0.1700
Data Index: 4266712 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19