Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.3725. Min Act: -0.1700
Data Index: 6982062 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.2162. Min Act: -0.1700
Data Index: 1435051 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.1537. Min Act: -0.1700
Data Index: 5636434 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0912. Min Act: -0.1700
Data Index: 850243 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.1225. Min Act: -0.1700
Data Index: 8124099 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0912. Min Act: -0.1700
Data Index: 4253609 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0600. Min Act: -0.1700
Data Index: 477123 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0287. Min Act: -0.1700
Data Index: 4167258 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0600. Min Act: -0.1700
Data Index: 632899 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0287. Min Act: -0.1700
Data Index: 2502807 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0287. Min Act: -0.1700
Data Index: 2684673 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9975. Min Act: -0.1700
Data Index: 5699653 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3725. Min Range: -6.3725
Max Act: 6.0287. Min Act: -0.1700
Data Index: 7491589 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2647085 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9975. Min Act: -0.1700
Data Index: 6971108 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2509012 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9662. Min Act: -0.1700
Data Index: 3926860 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9662. Min Act: -0.1700
Data Index: 673286 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9350. Min Act: -0.1700
Data Index: 261345 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3725. Min Range: -6.3725
Max Act: 5.9350. Min Act: -0.1700
Data Index: 874486 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19