Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.3389. Min Act: -0.1700
Data Index: 8515101 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.3076. Min Act: -0.1700
Data Index: 5303976 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1514. Min Act: -0.1700
Data Index: 2636398 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 5998509 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 6961455 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1583210 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0576. Min Act: -0.1700
Data Index: 1392441 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0264. Min Act: -0.1700
Data Index: 962470 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0264. Min Act: -0.1700
Data Index: 8039042 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.9951. Min Act: -0.1700
Data Index: 6056759 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.9639. Min Act: -0.1700
Data Index: 7644036 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.9326. Min Act: -0.1700
Data Index: 5380707 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.9326. Min Act: -0.1700
Data Index: 6039849 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.9326. Min Act: -0.1700
Data Index: 3472466 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.8701. Min Act: -0.1700
Data Index: 7854046 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.8701. Min Act: -0.1700
Data Index: 4341243 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.8389. Min Act: -0.1700
Data Index: 77188 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.8076. Min Act: -0.1700
Data Index: 7039627 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.8389. Min Act: -0.1700
Data Index: 7142187 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3389. Min Range: -5.3389
Max Act: 4.8076. Min Act: -0.1700
Data Index: 5055874 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19