Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1366 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5844. Min Act: -0.1700
Data Index: 8235200 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5219. Min Act: -0.1700
Data Index: 836052 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 5461140 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5219. Min Act: -0.1700
Data Index: 4796330 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5531. Min Act: -0.1700
Data Index: 380676 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5219. Min Act: -0.1700
Data Index: 3516836 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5219. Min Act: -0.1700
Data Index: 7134377 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 7161514 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5219. Min Act: -0.1700
Data Index: 7527882 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5219. Min Act: -0.1700
Data Index: 395454 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 219175 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 1912523 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 3662047 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 8203818 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 4325990 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.5219. Min Act: -0.1700
Data Index: 8640653 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 6411183 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4594. Min Act: -0.1700
Data Index: 768306 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 4829371 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5844. Min Range: -4.5844
Max Act: 4.4906. Min Act: -0.1700
Data Index: 6247525 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19