Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2456. Min Range: -6.2456
Max Act: 6.2456. Min Act: -0.1700
Data Index: 6638323 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2456. Min Range: -6.2456
Max Act: 6.2143. Min Act: -0.1700
Data Index: 801468 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2456. Min Range: -6.2456
Max Act: 6.2143. Min Act: -0.1700
Data Index: 6992445 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2456. Min Range: -6.2456
Max Act: 6.0893. Min Act: -0.1700
Data Index: 2443672 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2456. Min Range: -6.2456
Max Act: 6.0893. Min Act: -0.1700
Data Index: 5114149 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2456. Min Range: -6.2456
Max Act: 6.0268. Min Act: -0.1700
Data Index: 2313572 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2456. Min Range: -6.2456
Max Act: 6.0268. Min Act: -0.1700
Data Index: 2423174 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.9643. Min Act: -0.1700
Data Index: 1537633 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.9643. Min Act: -0.1700
Data Index: 4279377 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.9018. Min Act: -0.1700
Data Index: 223249 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.8706. Min Act: -0.1700
Data Index: 315361 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.8706. Min Act: -0.1700
Data Index: 2177571 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.8393. Min Act: -0.1700
Data Index: 1608693 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.8393. Min Act: -0.1700
Data Index: 5450376 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.8393. Min Act: -0.1700
Data Index: 2763658 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.8081. Min Act: -0.1700
Data Index: 8129874 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.7768. Min Act: -0.1700
Data Index: 7607078 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.8081. Min Act: -0.1700
Data Index: 6591346 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.7768. Min Act: -0.1700
Data Index: 1457601 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2456. Min Range: -6.2456
Max Act: 5.7768. Min Act: -0.1700
Data Index: 4024760 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19