Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4174 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0599. Min Range: -5.0599
Max Act: 5.0599. Min Act: -0.1700
Data Index: 1544630 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0599. Min Range: -5.0599
Max Act: 5.0599. Min Act: -0.1700
Data Index: 1472682 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0599. Min Range: -5.0599
Max Act: 5.0599. Min Act: -0.1700
Data Index: 1087965 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0599. Min Range: -5.0599
Max Act: 5.0287. Min Act: -0.1700
Data Index: 1542799 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0599. Min Range: -5.0599
Max Act: 5.0287. Min Act: -0.1700
Data Index: 2763867 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9974. Min Act: -0.1700
Data Index: 4646208 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9974. Min Act: -0.1700
Data Index: 6491247 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9349. Min Act: -0.1700
Data Index: 8615113 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9349. Min Act: -0.1700
Data Index: 2593339 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9349. Min Act: -0.1700
Data Index: 919976 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9349. Min Act: -0.1700
Data Index: 6319374 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9037. Min Act: -0.1700
Data Index: 976049 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9037. Min Act: -0.1700
Data Index: 6465134 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9037. Min Act: -0.1700
Data Index: 4341836 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9037. Min Act: -0.1700
Data Index: 8435131 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.9037. Min Act: -0.1700
Data Index: 6953919 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.8412. Min Act: -0.1700
Data Index: 4331053 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.8724. Min Act: -0.1700
Data Index: 4331054 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.8724. Min Act: -0.1700
Data Index: 3556393 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0599. Min Range: -5.0599
Max Act: 4.8724. Min Act: -0.1700
Data Index: 60152 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19