Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.8322. Min Act: -0.1700
Data Index: 8570390 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.4572. Min Act: -0.1700
Data Index: 780329 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.4572. Min Act: -0.1700
Data Index: 5986674 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.3010. Min Act: -0.1700
Data Index: 2428979 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.1760. Min Act: -0.1700
Data Index: 6818422 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.1135. Min Act: -0.1700
Data Index: 1165791 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.1135. Min Act: -0.1700
Data Index: 4001148 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.1135. Min Act: -0.1700
Data Index: 8233943 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.1135. Min Act: -0.1700
Data Index: 648411 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.0822. Min Act: -0.1700
Data Index: 2668708 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.0510. Min Act: -0.1700
Data Index: 2990084 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.0510. Min Act: -0.1700
Data Index: 7312628 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.0197. Min Act: -0.1700
Data Index: 6215593 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.0197. Min Act: -0.1700
Data Index: 716689 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8322. Min Range: -8.8322
Max Act: 7.9885. Min Act: -0.1700
Data Index: 6671299 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8322. Min Range: -8.8322
Max Act: 8.0197. Min Act: -0.1700
Data Index: 4973454 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8322. Min Range: -8.8322
Max Act: 7.9572. Min Act: -0.1700
Data Index: 7858275 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8322. Min Range: -8.8322
Max Act: 7.9260. Min Act: -0.1700
Data Index: 2783818 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8322. Min Range: -8.8322
Max Act: 7.8947. Min Act: -0.1700
Data Index: 6071571 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8322. Min Range: -8.8322
Max Act: 7.8947. Min Act: -0.1700
Data Index: 7618365 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19