Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5702 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.3433. Min Act: -0.1700
Data Index: 4998584 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.2808. Min Act: -0.1700
Data Index: 6509716 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.2808. Min Act: -0.1700
Data Index: 6377983 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.2808. Min Act: -0.1700
Data Index: 3621239 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.2496. Min Act: -0.1700
Data Index: 7775434 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.2496. Min Act: -0.1700
Data Index: 5921406 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.2808. Min Act: -0.1700
Data Index: 6623805 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.0933. Min Act: -0.1700
Data Index: 8495061 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.1246. Min Act: -0.1700
Data Index: 4030816 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.0308. Min Act: -0.1700
Data Index: 2292619 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.9996. Min Act: -0.1700
Data Index: 5167443 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3433. Min Range: -7.3433
Max Act: 7.0308. Min Act: -0.1700
Data Index: 1177046 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.9996. Min Act: -0.1700
Data Index: 4988348 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.9371. Min Act: -0.1700
Data Index: 2961814 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.9371. Min Act: -0.1700
Data Index: 2795781 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.9371. Min Act: -0.1700
Data Index: 4195084 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.9371. Min Act: -0.1700
Data Index: 8138704 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.9371. Min Act: -0.1700
Data Index: 677688 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.8746. Min Act: -0.1700
Data Index: 785106 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3433. Min Range: -7.3433
Max Act: 6.8746. Min Act: -0.1700
Data Index: 2057950 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19