Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.4662. Min Act: -0.1700
Data Index: 89509 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.4037. Min Act: -0.1700
Data Index: 1578771 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.3412. Min Act: -0.1700
Data Index: 7152397 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.1537. Min Act: -0.1700
Data Index: 1402460 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.1537. Min Act: -0.1700
Data Index: 7325993 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.1224. Min Act: -0.1700
Data Index: 2688240 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.0599. Min Act: -0.1700
Data Index: 723968 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.0599. Min Act: -0.1700
Data Index: 3338443 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4662. Min Range: -6.4662
Max Act: 6.0599. Min Act: -0.1700
Data Index: 4448780 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9974. Min Act: -0.1700
Data Index: 8582441 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9974. Min Act: -0.1700
Data Index: 3068872 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9974. Min Act: -0.1700
Data Index: 3720300 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9974. Min Act: -0.1700
Data Index: 5144835 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9974. Min Act: -0.1700
Data Index: 2570400 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2195203 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9662. Min Act: -0.1700
Data Index: 4525355 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9349. Min Act: -0.1700
Data Index: 3542355 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9349. Min Act: -0.1700
Data Index: 8449003 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9349. Min Act: -0.1700
Data Index: 8720103 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4662. Min Range: -6.4662
Max Act: 5.9037. Min Act: -0.1700
Data Index: 1280908 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19