Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0532. Min Range: -5.0532
Max Act: 5.0532. Min Act: -0.1700
Data Index: 4890257 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0532. Min Range: -5.0532
Max Act: 5.0219. Min Act: -0.1700
Data Index: 5718909 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.8969. Min Act: -0.1700
Data Index: 4776807 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.8657. Min Act: -0.1700
Data Index: 7131099 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.8032. Min Act: -0.1700
Data Index: 2255300 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.8032. Min Act: -0.1700
Data Index: 7005879 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.8032. Min Act: -0.1700
Data Index: 5405157 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.7719. Min Act: -0.1700
Data Index: 6596331 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.7719. Min Act: -0.1700
Data Index: 2867917 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.7407. Min Act: -0.1700
Data Index: 3828216 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.7094. Min Act: -0.1700
Data Index: 3512968 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.7407. Min Act: -0.1700
Data Index: 3111012 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.7094. Min Act: -0.1700
Data Index: 4996319 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.6782. Min Act: -0.1700
Data Index: 4049684 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.7094. Min Act: -0.1700
Data Index: 4769636 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.6469. Min Act: -0.1700
Data Index: 6096855 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.6469. Min Act: -0.1700
Data Index: 4102662 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.6469. Min Act: -0.1700
Data Index: 6270562 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.6469. Min Act: -0.1700
Data Index: 6521756 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0532. Min Range: -5.0532
Max Act: 4.6469. Min Act: -0.1700
Data Index: 1411588 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19