Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.3330. Min Act: -0.1700
Data Index: 1902908 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.1455. Min Act: -0.1700
Data Index: 4705329 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.5830. Min Act: -0.1700
Data Index: 8308297 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.1455. Min Act: -0.1700
Data Index: 1763189 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.0830. Min Act: -0.1700
Data Index: 4459081 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.4893. Min Act: -0.1700
Data Index: 5926973 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.8330. Min Act: -0.1700
Data Index: 4397917 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.3955. Min Act: -0.1700
Data Index: 4332502 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.9580. Min Act: -0.1700
Data Index: 6508360 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.1455. Min Act: -0.1700
Data Index: 3648731 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.9580. Min Act: -0.1700
Data Index: 1478472 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.9580. Min Act: -0.1700
Data Index: 3035005 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.5518. Min Act: -0.1700
Data Index: 2156295 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.6455. Min Act: -0.1700
Data Index: 7479603 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5830. Min Range: -7.5830
Max Act: 5.5830. Min Act: -0.1700
Data Index: 7202334 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.8330. Min Act: -0.1700
Data Index: 7626658 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.8330. Min Act: -0.1700
Data Index: 2487369 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.3018. Min Act: -0.1700
Data Index: 5085476 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5830. Min Range: -7.5830
Max Act: 7.3018. Min Act: -0.1700
Data Index: 5462584 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5830. Min Range: -7.5830
Max Act: 6.8018. Min Act: -0.1700
Data Index: 5456462 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19