Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3455. Min Range: -6.3455
Max Act: 6.3455. Min Act: -0.1700
Data Index: 6882037 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3455. Min Range: -6.3455
Max Act: 6.0018. Min Act: -0.1700
Data Index: 1361017 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.9393. Min Act: -0.1700
Data Index: 7547881 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.9080. Min Act: -0.1700
Data Index: 1467855 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.9393. Min Act: -0.1700
Data Index: 1014767 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.9705. Min Act: -0.1700
Data Index: 8336666 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.9080. Min Act: -0.1700
Data Index: 5511175 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.9080. Min Act: -0.1700
Data Index: 7342377 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.9080. Min Act: -0.1700
Data Index: 6741409 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.8455. Min Act: -0.1700
Data Index: 5245424 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.7518. Min Act: -0.1700
Data Index: 8164710 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.7830. Min Act: -0.1700
Data Index: 3959634 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.8143. Min Act: -0.1700
Data Index: 2666699 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.7518. Min Act: -0.1700
Data Index: 4378668 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.7518. Min Act: -0.1700
Data Index: 6712056 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.7205. Min Act: -0.1700
Data Index: 3219984 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.7205. Min Act: -0.1700
Data Index: 4212467 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.7205. Min Act: -0.1700
Data Index: 348388 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.6893. Min Act: -0.1700
Data Index: 6919514 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3455. Min Range: -6.3455
Max Act: 5.6580. Min Act: -0.1700
Data Index: 3859136 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19