Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4780 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2287. Min Range: -7.2287
Max Act: 7.2287. Min Act: -0.1700
Data Index: 5233419 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2287. Min Range: -7.2287
Max Act: 7.1037. Min Act: -0.1700
Data Index: 8210579 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2287. Min Range: -7.2287
Max Act: 7.0412. Min Act: -0.1700
Data Index: 629312 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2287. Min Range: -7.2287
Max Act: 7.0099. Min Act: -0.1700
Data Index: 2336153 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.9787. Min Act: -0.1700
Data Index: 3020624 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.9474. Min Act: -0.1700
Data Index: 78896 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.9162. Min Act: -0.1700
Data Index: 5389610 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.8849. Min Act: -0.1700
Data Index: 7653574 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.7912. Min Act: -0.1700
Data Index: 3835574 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.7599. Min Act: -0.1700
Data Index: 8725168 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.7287. Min Act: -0.1700
Data Index: 2690152 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.7287. Min Act: -0.1700
Data Index: 6856411 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.6662. Min Act: -0.1700
Data Index: 7464143 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.6662. Min Act: -0.1700
Data Index: 1781872 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.6349. Min Act: -0.1700
Data Index: 4696701 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.6349. Min Act: -0.1700
Data Index: 1873027 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.6349. Min Act: -0.1700
Data Index: 4421465 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.6037. Min Act: -0.1700
Data Index: 8700619 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.6037. Min Act: -0.1700
Data Index: 3951482 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2287. Min Range: -7.2287
Max Act: 6.5724. Min Act: -0.1700
Data Index: 2191890 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19