Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3887 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.4206. Min Act: -0.1700
Data Index: 5532773 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.2643. Min Act: -0.1700
Data Index: 482847 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.2018. Min Act: -0.1700
Data Index: 2617260 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.2331. Min Act: -0.1700
Data Index: 3067708 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.1706. Min Act: -0.1700
Data Index: 5532775 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.2018. Min Act: -0.1700
Data Index: 908186 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.1081. Min Act: -0.1700
Data Index: 5532776 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.1081. Min Act: -0.1700
Data Index: 2723829 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.0768. Min Act: -0.1700
Data Index: 2117550 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.0768. Min Act: -0.1700
Data Index: 482848 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.0456. Min Act: -0.1700
Data Index: 482846 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.0143. Min Act: -0.1700
Data Index: 3516209 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.0456. Min Act: -0.1700
Data Index: 7766305 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4206. Min Range: -5.4206
Max Act: 5.0143. Min Act: -0.1700
Data Index: 7708027 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4206. Min Range: -5.4206
Max Act: 4.9831. Min Act: -0.1700
Data Index: 4278556 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4206. Min Range: -5.4206
Max Act: 4.9831. Min Act: -0.1700
Data Index: 172857 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4206. Min Range: -5.4206
Max Act: 4.9831. Min Act: -0.1700
Data Index: 3321373 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4206. Min Range: -5.4206
Max Act: 4.9831. Min Act: -0.1700
Data Index: 2723830 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4206. Min Range: -5.4206
Max Act: 4.9831. Min Act: -0.1700
Data Index: 7708026 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4206. Min Range: -5.4206
Max Act: 4.9831. Min Act: -0.1700
Data Index: 7693807 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19