Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 298 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.5290. Min Act: -0.1700
Data Index: 4298896 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.4040. Min Act: -0.1700
Data Index: 1380198 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.3415. Min Act: -0.1700
Data Index: 7557225 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.3415. Min Act: -0.1700
Data Index: 6110727 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.3415. Min Act: -0.1700
Data Index: 5995474 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.2790. Min Act: -0.1700
Data Index: 5754342 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.2790. Min Act: -0.1700
Data Index: 4189217 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.1540. Min Act: -0.1700
Data Index: 4945874 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.1540. Min Act: -0.1700
Data Index: 6297782 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.2165. Min Act: -0.1700
Data Index: 1492422 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.1540. Min Act: -0.1700
Data Index: 5900325 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.0915. Min Act: -0.1700
Data Index: 8144341 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.0915. Min Act: -0.1700
Data Index: 3045123 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.0915. Min Act: -0.1700
Data Index: 4409709 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.0290. Min Act: -0.1700
Data Index: 2355 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5290. Min Range: -10.5290
Max Act: 9.9665. Min Act: -0.1700
Data Index: 6472368 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5290. Min Range: -10.5290
Max Act: 9.9665. Min Act: -0.1700
Data Index: 1992485 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5290. Min Range: -10.5290
Max Act: 10.0290. Min Act: -0.1700
Data Index: 4343892 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5290. Min Range: -10.5290
Max Act: 9.9665. Min Act: -0.1700
Data Index: 2034778 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5290. Min Range: -10.5290
Max Act: 9.9665. Min Act: -0.1700
Data Index: 3050597 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19