Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.8816. Min Act: -0.1700
Data Index: 8576103 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.6004. Min Act: -0.1700
Data Index: 2079206 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.5066. Min Act: -0.1700
Data Index: 5467497 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.4754. Min Act: -0.1700
Data Index: 3492651 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.4129. Min Act: -0.1700
Data Index: 4676996 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.4129. Min Act: -0.1700
Data Index: 2719865 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.4129. Min Act: -0.1700
Data Index: 8727108 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.4129. Min Act: -0.1700
Data Index: 178498 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.3816. Min Act: -0.1700
Data Index: 2788393 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.3504. Min Act: -0.1700
Data Index: 421779 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.3504. Min Act: -0.1700
Data Index: 6460317 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.3191. Min Act: -0.1700
Data Index: 5547349 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.3504. Min Act: -0.1700
Data Index: 7212617 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.3191. Min Act: -0.1700
Data Index: 7705026 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.3191. Min Act: -0.1700
Data Index: 6030642 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.2879. Min Act: -0.1700
Data Index: 8386503 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.2879. Min Act: -0.1700
Data Index: 3585007 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.2566. Min Act: -0.1700
Data Index: 5922223 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.2879. Min Act: -0.1700
Data Index: 8261696 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8816. Min Range: -5.8816
Max Act: 5.2566. Min Act: -0.1700
Data Index: 1945697 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19