Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.3340. Min Act: -0.1700
Data Index: 8023677 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.2712. Min Act: -0.1700
Data Index: 918944 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.1455. Min Act: -0.1700
Data Index: 4160284 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.1297. Min Act: -0.1700
Data Index: 2077265 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.1455. Min Act: -0.1700
Data Index: 7865574 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.0982. Min Act: -0.1700
Data Index: 5622071 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.1140. Min Act: -0.1700
Data Index: 213443 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.0982. Min Act: -0.1700
Data Index: 7608060 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.0509. Min Act: -0.1700
Data Index: 6863563 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.0351. Min Act: -0.1700
Data Index: 6933908 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.0035. Min Act: -0.1700
Data Index: 1656425 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9877. Min Act: -0.1700
Data Index: 4194169 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9402. Min Act: -0.1700
Data Index: 6309202 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9877. Min Act: -0.1700
Data Index: 5452647 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9719. Min Act: -0.1700
Data Index: 6101070 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9561. Min Act: -0.1700
Data Index: 4201383 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9877. Min Act: -0.1700
Data Index: 1325013 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9877. Min Act: -0.1700
Data Index: 2978922 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3340. Min Range: -3.3340
Max Act: 3.0035. Min Act: -0.1700
Data Index: 2553823 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3340. Min Range: -3.3340
Max Act: 2.9877. Min Act: -0.1700
Data Index: 4995353 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19