Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 359 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.5213. Min Act: -0.1700
Data Index: 715630 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3651. Min Act: -0.1700
Data Index: 8594614 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3651. Min Act: -0.1700
Data Index: 7643066 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.0838. Min Act: -0.1700
Data Index: 2412080 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.0526. Min Act: -0.1700
Data Index: 7275853 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.0526. Min Act: -0.1700
Data Index: 7275858 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.9901. Min Act: -0.1700
Data Index: 2412081 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.9276. Min Act: -0.1700
Data Index: 4482547 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.8651. Min Act: -0.1700
Data Index: 3523860 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.8651. Min Act: -0.1700
Data Index: 1688234 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.8338. Min Act: -0.1700
Data Index: 4680752 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.8026. Min Act: -0.1700
Data Index: 5738463 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.8026. Min Act: -0.1700
Data Index: 5760064 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.7401. Min Act: -0.1700
Data Index: 548177 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.7401. Min Act: -0.1700
Data Index: 8046149 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.7401. Min Act: -0.1700
Data Index: 2149713 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.7401. Min Act: -0.1700
Data Index: 6678836 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.7088. Min Act: -0.1700
Data Index: 7919960 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.6776. Min Act: -0.1700
Data Index: 7795977 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5213. Min Range: -5.5213
Max Act: 4.6776. Min Act: -0.1700
Data Index: 5706493 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19