Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0685. Min Act: -0.1700
Data Index: 8027589 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0528. Min Act: -0.1700
Data Index: 8321699 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0370. Min Act: -0.1700
Data Index: 1953708 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0685. Min Range: -3.0685
Max Act: 3.0054. Min Act: -0.1700
Data Index: 6207948 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9896. Min Act: -0.1700
Data Index: 1853092 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9896. Min Act: -0.1700
Data Index: 4430414 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9579. Min Act: -0.1700
Data Index: 6207937 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9579. Min Act: -0.1700
Data Index: 4448328 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9579. Min Act: -0.1700
Data Index: 4345792 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9421. Min Act: -0.1700
Data Index: 6809129 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9421. Min Act: -0.1700
Data Index: 3446942 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9263. Min Act: -0.1700
Data Index: 3988831 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9263. Min Act: -0.1700
Data Index: 8444482 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9263. Min Act: -0.1700
Data Index: 8797161 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9263. Min Act: -0.1700
Data Index: 7866559 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.9104. Min Act: -0.1700
Data Index: 553915 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8946. Min Act: -0.1700
Data Index: 4858858 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8946. Min Act: -0.1700
Data Index: 1443511 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8787. Min Act: -0.1700
Data Index: 3765064 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0685. Min Range: -3.0685
Max Act: 2.8787. Min Act: -0.1700
Data Index: 6195414 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19