Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 102 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2076. Min Range: -6.2076
Max Act: 6.2076. Min Act: -0.1700
Data Index: 8057068 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2076. Min Range: -6.2076
Max Act: 6.0513. Min Act: -0.1700
Data Index: 8400908 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.9888. Min Act: -0.1700
Data Index: 7191506 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.9888. Min Act: -0.1700
Data Index: 8306132 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.9888. Min Act: -0.1700
Data Index: 4642702 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.9576. Min Act: -0.1700
Data Index: 467848 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8951. Min Act: -0.1700
Data Index: 3865134 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.9263. Min Act: -0.1700
Data Index: 4087635 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8951. Min Act: -0.1700
Data Index: 2660307 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8951. Min Act: -0.1700
Data Index: 6188301 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8638. Min Act: -0.1700
Data Index: 2338961 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8638. Min Act: -0.1700
Data Index: 8114755 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8638. Min Act: -0.1700
Data Index: 8057066 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8326. Min Act: -0.1700
Data Index: 8400903 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8326. Min Act: -0.1700
Data Index: 6417504 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8013. Min Act: -0.1700
Data Index: 4103307 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8326. Min Act: -0.1700
Data Index: 5890728 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8013. Min Act: -0.1700
Data Index: 6210813 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.7701. Min Act: -0.1700
Data Index: 7034785 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2076. Min Range: -6.2076
Max Act: 5.8013. Min Act: -0.1700
Data Index: 8057067 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19