Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5201. Min Range: -7.5201
Max Act: 7.5201. Min Act: -0.1700
Data Index: 3712599 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5201. Min Range: -7.5201
Max Act: 7.3638. Min Act: -0.1700
Data Index: 6220089 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5201. Min Range: -7.5201
Max Act: 7.1451. Min Act: -0.1700
Data Index: 8328279 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.9263. Min Act: -0.1700
Data Index: 2176565 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.8951. Min Act: -0.1700
Data Index: 2666416 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.8638. Min Act: -0.1700
Data Index: 2318600 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.8326. Min Act: -0.1700
Data Index: 3864664 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.8326. Min Act: -0.1700
Data Index: 6409388 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.8013. Min Act: -0.1700
Data Index: 783615 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.8013. Min Act: -0.1700
Data Index: 6866227 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7701. Min Act: -0.1700
Data Index: 564040 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7701. Min Act: -0.1700
Data Index: 2355783 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7076. Min Act: -0.1700
Data Index: 900823 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7388. Min Act: -0.1700
Data Index: 2336930 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7388. Min Act: -0.1700
Data Index: 6159206 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7076. Min Act: -0.1700
Data Index: 6571202 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7076. Min Act: -0.1700
Data Index: 1196524 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.6763. Min Act: -0.1700
Data Index: 5378429 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.7076. Min Act: -0.1700
Data Index: 768899 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5201. Min Range: -7.5201
Max Act: 6.6763. Min Act: -0.1700
Data Index: 2177987 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19