Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.2867. Min Act: -0.1700
Data Index: 3581542 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1929. Min Act: -0.1700
Data Index: 6581597 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1929. Min Act: -0.1700
Data Index: 56038 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1617. Min Act: -0.1700
Data Index: 919015 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 5520972 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 2607887 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 7457368 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 6408660 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 5253455 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.1304. Min Act: -0.1700
Data Index: 6372457 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 6501094 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 2089330 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0992. Min Act: -0.1700
Data Index: 5019994 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 6347351 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0367. Min Act: -0.1700
Data Index: 2017478 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 8255730 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 3558444 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 6585523 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 4026198 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2867. Min Range: -5.2867
Max Act: 5.0679. Min Act: -0.1700
Data Index: 1316161 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19