Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5314 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1879. Min Range: -7.1879
Max Act: 7.1879. Min Act: -0.1700
Data Index: 5635888 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1879. Min Range: -7.1879
Max Act: 7.0316. Min Act: -0.1700
Data Index: 3871849 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.9691. Min Act: -0.1700
Data Index: 7266695 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.9066. Min Act: -0.1700
Data Index: 1324683 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.8754. Min Act: -0.1700
Data Index: 4018739 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.8754. Min Act: -0.1700
Data Index: 5712656 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.8754. Min Act: -0.1700
Data Index: 6683766 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.8129. Min Act: -0.1700
Data Index: 6417086 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.8129. Min Act: -0.1700
Data Index: 2095919 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.7816. Min Act: -0.1700
Data Index: 974275 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.7504. Min Act: -0.1700
Data Index: 4577484 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.7504. Min Act: -0.1700
Data Index: 4936881 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.7191. Min Act: -0.1700
Data Index: 3655271 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.7191. Min Act: -0.1700
Data Index: 7323863 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.6879. Min Act: -0.1700
Data Index: 504308 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.6879. Min Act: -0.1700
Data Index: 5146174 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.7191. Min Act: -0.1700
Data Index: 4936854 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.6879. Min Act: -0.1700
Data Index: 974274 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.6566. Min Act: -0.1700
Data Index: 8302459 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1879. Min Range: -7.1879
Max Act: 6.6254. Min Act: -0.1700
Data Index: 110127 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19