Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1264 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.7771. Min Act: -0.1700
Data Index: 2013945 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.5271. Min Act: -0.1700
Data Index: 3723820 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.4646. Min Act: -0.1700
Data Index: 6417913 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.4646. Min Act: -0.1700
Data Index: 5234631 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.4646. Min Act: -0.1700
Data Index: 2431513 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.4333. Min Act: -0.1700
Data Index: 4300418 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.4021. Min Act: -0.1700
Data Index: 7591685 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.4021. Min Act: -0.1700
Data Index: 1711468 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.4021. Min Act: -0.1700
Data Index: 8247609 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3708. Min Act: -0.1700
Data Index: 4184871 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3708. Min Act: -0.1700
Data Index: 2349119 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3396. Min Act: -0.1700
Data Index: 5278516 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3396. Min Act: -0.1700
Data Index: 2100953 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3396. Min Act: -0.1700
Data Index: 6436429 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3396. Min Act: -0.1700
Data Index: 2447522 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3083. Min Act: -0.1700
Data Index: 7605271 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3083. Min Act: -0.1700
Data Index: 861087 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3083. Min Act: -0.1700
Data Index: 405576 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.3083. Min Act: -0.1700
Data Index: 2223968 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7771. Min Range: -5.7771
Max Act: 5.2771. Min Act: -0.1700
Data Index: 1350925 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19