Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.7444. Min Act: -0.1700
Data Index: 7649875 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.6819. Min Act: -0.1700
Data Index: 1094704 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.7132. Min Act: -0.1700
Data Index: 996316 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.6819. Min Act: -0.1700
Data Index: 6264574 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.6194. Min Act: -0.1700
Data Index: 2411542 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.5569. Min Act: -0.1700
Data Index: 6225600 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.5257. Min Act: -0.1700
Data Index: 4630107 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4632. Min Act: -0.1700
Data Index: 8006858 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4632. Min Act: -0.1700
Data Index: 2750368 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4319. Min Act: -0.1700
Data Index: 8165502 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4007. Min Act: -0.1700
Data Index: 8399939 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4007. Min Act: -0.1700
Data Index: 6328296 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4007. Min Act: -0.1700
Data Index: 477657 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4007. Min Act: -0.1700
Data Index: 3761282 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.4007. Min Act: -0.1700
Data Index: 5285214 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.3382. Min Act: -0.1700
Data Index: 5764154 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.3069. Min Act: -0.1700
Data Index: 4384943 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.3694. Min Act: -0.1700
Data Index: 1985025 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.3382. Min Act: -0.1700
Data Index: 3349993 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7444. Min Range: -6.7444
Max Act: 6.2757. Min Act: -0.1700
Data Index: 8777597 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19