Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1240 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.6406. Min Act: -0.1700
Data Index: 8106057 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.3281. Min Act: -0.1700
Data Index: 3539865 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.2656. Min Act: -0.1700
Data Index: 3860254 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.2656. Min Act: -0.1700
Data Index: 2313372 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.2343. Min Act: -0.1700
Data Index: 213490 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.2031. Min Act: -0.1700
Data Index: 3200500 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.2031. Min Act: -0.1700
Data Index: 2063115 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.2031. Min Act: -0.1700
Data Index: 6432324 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.2031. Min Act: -0.1700
Data Index: 6752844 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.1718. Min Act: -0.1700
Data Index: 2063116 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.1405. Min Act: -0.1700
Data Index: 140841 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.1405. Min Act: -0.1700
Data Index: 908136 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.1405. Min Act: -0.1700
Data Index: 8787091 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.1093. Min Act: -0.1700
Data Index: 7617760 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.1093. Min Act: -0.1700
Data Index: 5210374 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.1093. Min Act: -0.1700
Data Index: 3611787 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.0780. Min Act: -0.1700
Data Index: 5297540 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.0155. Min Act: -0.1700
Data Index: 1571242 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.0155. Min Act: -0.1700
Data Index: 7102642 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6406. Min Range: -4.6406
Max Act: 4.0468. Min Act: -0.1700
Data Index: 8357906 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19