Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3342 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.4161. Min Act: -0.1700
Data Index: 7230220 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.3536. Min Act: -0.1700
Data Index: 1747666 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.2599. Min Act: -0.1700
Data Index: 4614008 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.1349. Min Act: -0.1700
Data Index: 6184274 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.1349. Min Act: -0.1700
Data Index: 3370 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.0724. Min Act: -0.1700
Data Index: 7945616 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.0724. Min Act: -0.1700
Data Index: 5989097 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.0724. Min Act: -0.1700
Data Index: 1526028 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.0099. Min Act: -0.1700
Data Index: 7035666 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.0411. Min Act: -0.1700
Data Index: 3701222 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.0099. Min Act: -0.1700
Data Index: 1611469 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4161. Min Range: -5.4161
Max Act: 5.0099. Min Act: -0.1700
Data Index: 2400041 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.9786. Min Act: -0.1700
Data Index: 8807021 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.9474. Min Act: -0.1700
Data Index: 2703576 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.9161. Min Act: -0.1700
Data Index: 1514276 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.9161. Min Act: -0.1700
Data Index: 3900986 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.9161. Min Act: -0.1700
Data Index: 5082286 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.9161. Min Act: -0.1700
Data Index: 1597210 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.8849. Min Act: -0.1700
Data Index: 8504552 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4161. Min Range: -5.4161
Max Act: 4.8536. Min Act: -0.1700
Data Index: 2399409 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19