Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.3244. Min Act: -0.1700
Data Index: 1571028 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.3401. Min Act: -0.1700
Data Index: 8223512 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.3087. Min Act: -0.1700
Data Index: 993309 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2773. Min Act: -0.1700
Data Index: 6852303 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2616. Min Act: -0.1700
Data Index: 5093254 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 1309171 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2616. Min Act: -0.1700
Data Index: 7652722 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2616. Min Act: -0.1700
Data Index: 6852302 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 638135 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 8306872 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 2058916 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2616. Min Act: -0.1700
Data Index: 2341346 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 8756745 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 2462421 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 1263314 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 3477100 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2302. Min Act: -0.1700
Data Index: 5101993 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2302. Min Act: -0.1700
Data Index: 6424041 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2302. Min Act: -0.1700
Data Index: 519987 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3401. Min Range: -3.3401
Max Act: 3.2459. Min Act: -0.1700
Data Index: 2999608 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19