Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.7784. Min Act: -0.1700
Data Index: 290883 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.7471. Min Act: -0.1700
Data Index: 5926629 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.6846. Min Act: -0.1698
Data Index: 290882 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.5596. Min Act: -0.1700
Data Index: 5926630 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.4346. Min Act: -0.1698
Data Index: 4283145 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.4034. Min Act: -0.1700
Data Index: 538223 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.3721. Min Act: -0.1700
Data Index: 4091839 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.3409. Min Act: -0.1700
Data Index: 3608624 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.2471. Min Act: -0.1700
Data Index: 290879 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.1534. Min Act: -0.1700
Data Index: 2650275 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.1534. Min Act: -0.1700
Data Index: 2847736 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.1221. Min Act: -0.1700
Data Index: 6647579 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.0909. Min Act: -0.1700
Data Index: 3735258 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 6848771 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 6584907 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7784. Min Range: -5.7784
Max Act: 4.9971. Min Act: -0.1700
Data Index: 7978246 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 2650274 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7784. Min Range: -5.7784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 3012335 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7784. Min Range: -5.7784
Max Act: 4.9971. Min Act: -0.1700
Data Index: 538222 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7784. Min Range: -5.7784
Max Act: 4.9971. Min Act: -0.1700
Data Index: 5795334 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19