Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5702 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3400. Min Range: -8.3400
Max Act: 8.3400. Min Act: -0.1700
Data Index: 6599562 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3400. Min Range: -8.3400
Max Act: 8.3400. Min Act: -0.1700
Data Index: 5778319 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3400. Min Range: -8.3400
Max Act: 8.2150. Min Act: -0.1700
Data Index: 1618130 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3400. Min Range: -8.3400
Max Act: 8.1525. Min Act: -0.1700
Data Index: 7123036 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3400. Min Range: -8.3400
Max Act: 8.0900. Min Act: -0.1700
Data Index: 8737586 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3400. Min Range: -8.3400
Max Act: 8.0275. Min Act: -0.1700
Data Index: 3080428 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3400. Min Range: -8.3400
Max Act: 8.0275. Min Act: -0.1700
Data Index: 5634513 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9650. Min Act: -0.1700
Data Index: 3781920 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9650. Min Act: -0.1700
Data Index: 4644188 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9650. Min Act: -0.1700
Data Index: 1123241 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9650. Min Act: -0.1700
Data Index: 6696854 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9338. Min Act: -0.1700
Data Index: 4601577 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9338. Min Act: -0.1700
Data Index: 5944858 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9338. Min Act: -0.1700
Data Index: 6047072 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9025. Min Act: -0.1700
Data Index: 5893844 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9025. Min Act: -0.1700
Data Index: 267642 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9025. Min Act: -0.1700
Data Index: 4729323 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.9025. Min Act: -0.1700
Data Index: 6868979 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.8713. Min Act: -0.1700
Data Index: 2981077 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3400. Min Range: -8.3400
Max Act: 7.8713. Min Act: -0.1700
Data Index: 3665744 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19