Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.1577. Min Act: -0.1700
Data Index: 4492500 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.1104. Min Act: -0.1700
Data Index: 8514399 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0947. Min Act: -0.1700
Data Index: 3910836 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0789. Min Act: -0.1700
Data Index: 3850258 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0947. Min Act: -0.1700
Data Index: 772472 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0789. Min Act: -0.1700
Data Index: 284882 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0473. Min Act: -0.1700
Data Index: 3319734 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0316. Min Act: -0.1700
Data Index: 3581717 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0158. Min Act: -0.1700
Data Index: 3508111 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0158. Min Act: -0.1700
Data Index: 2577990 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0158. Min Act: -0.1700
Data Index: 3110791 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0158. Min Act: -0.1700
Data Index: 1363171 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0316. Min Act: -0.1700
Data Index: 3136627 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0000. Min Act: -0.1700
Data Index: 3464684 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0000. Min Act: -0.1700
Data Index: 7371210 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1577. Min Range: -3.1577
Max Act: 2.9841. Min Act: -0.1700
Data Index: 4608893 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0000. Min Act: -0.1700
Data Index: 6969657 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0000. Min Act: -0.1700
Data Index: 4357800 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1577. Min Range: -3.1577
Max Act: 3.0000. Min Act: -0.1700
Data Index: 3091177 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1577. Min Range: -3.1577
Max Act: 2.9841. Min Act: -0.1700
Data Index: 1886312 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19