Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0232. Min Range: -8.0232
Max Act: 8.0232. Min Act: -0.1700
Data Index: 6805200 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.9607. Min Act: -0.1700
Data Index: 5464070 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.8357. Min Act: -0.1700
Data Index: 6243424 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.7732. Min Act: -0.1700
Data Index: 5444375 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.7732. Min Act: -0.1700
Data Index: 4192214 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.7732. Min Act: -0.1700
Data Index: 4703636 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.5232. Min Act: -0.1700
Data Index: 1058641 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.4607. Min Act: -0.1700
Data Index: 4717463 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.5232. Min Act: -0.1700
Data Index: 4717455 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.5232. Min Act: -0.1700
Data Index: 5310523 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.5232. Min Act: -0.1700
Data Index: 1205856 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.3982. Min Act: -0.1700
Data Index: 992684 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.3982. Min Act: -0.1700
Data Index: 3966363 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.4607. Min Act: -0.1700
Data Index: 7785580 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.4607. Min Act: -0.1700
Data Index: 1572466 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.3982. Min Act: -0.1700
Data Index: 3465904 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.4607. Min Act: -0.1700
Data Index: 8138252 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.4607. Min Act: -0.1700
Data Index: 8148898 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.4607. Min Act: -0.1700
Data Index: 4394296 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0232. Min Range: -8.0232
Max Act: 7.3982. Min Act: -0.1700
Data Index: 1975274 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19