Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 589 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.8550. Min Act: -0.1699
Data Index: 7146950 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5614791 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3480382 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.8237. Min Act: -0.1700
Data Index: 2380102 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.8237. Min Act: -0.1700
Data Index: 2257836 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7055258 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7925. Min Act: -0.1700
Data Index: 3676243 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7612. Min Act: -0.1700
Data Index: 8527142 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7612. Min Act: -0.1700
Data Index: 7495010 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7612. Min Act: -0.1700
Data Index: 2851830 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7612. Min Act: -0.1699
Data Index: 1913874 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7612. Min Act: -0.1700
Data Index: 5760619 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7612. Min Act: -0.1700
Data Index: 5536649 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7706329 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7300. Min Act: -0.1700
Data Index: 5928306 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7300. Min Act: -0.1700
Data Index: 2769515 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.6987. Min Act: -0.1700
Data Index: 3000257 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7300. Min Act: -0.1700
Data Index: 3896561 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7300. Min Act: -0.1700
Data Index: 6021342 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8550. Min Range: -5.8550
Max Act: 5.7300. Min Act: -0.1700
Data Index: 5247065 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19