Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2636. Min Range: -6.2636
Max Act: 4.4199. Min Act: -0.1700
Data Index: 291501 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.2636. Min Act: -0.1700
Data Index: 5651450 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.2636. Min Act: -0.1700
Data Index: 654237 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.2011. Min Act: -0.1700
Data Index: 719375 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2636. Min Range: -6.2636
Max Act: 4.9824. Min Act: -0.1700
Data Index: 4166310 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.2011. Min Act: -0.1700
Data Index: 719374 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.1386. Min Act: -0.1700
Data Index: 719377 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.1074. Min Act: -0.1700
Data Index: 3226769 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.1386. Min Act: -0.1700
Data Index: 6349962 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.1699. Min Act: -0.1700
Data Index: 719373 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2636. Min Range: -6.2636
Max Act: 5.6074. Min Act: -0.1700
Data Index: 2096865 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.0761. Min Act: -0.1700
Data Index: 719372 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.1074. Min Act: -0.1700
Data Index: 8569393 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.0449. Min Act: -0.1700
Data Index: 719376 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2636. Min Range: -6.2636
Max Act: 5.9824. Min Act: -0.1700
Data Index: 2731872 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2636. Min Range: -6.2636
Max Act: 5.9511. Min Act: -0.1700
Data Index: 6349967 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.0136. Min Act: -0.1700
Data Index: 743326 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2636. Min Range: -6.2636
Max Act: 6.0136. Min Act: -0.1700
Data Index: 6349957 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2636. Min Range: -6.2636
Max Act: 5.9824. Min Act: -0.1700
Data Index: 6349960 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2636. Min Range: -6.2636
Max Act: 5.9824. Min Act: -0.1700
Data Index: 4899728 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19