Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.7194. Min Act: -0.1700
Data Index: 3664419 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.6882. Min Act: -0.1700
Data Index: 2364121 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.6882. Min Act: -0.1700
Data Index: 1839606 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.6257. Min Act: -0.1700
Data Index: 2047568 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.6569. Min Act: -0.1700
Data Index: 465963 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.6257. Min Act: -0.1700
Data Index: 688856 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5944. Min Act: -0.1700
Data Index: 674306 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5944. Min Act: -0.1700
Data Index: 5900786 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5632. Min Act: -0.1700
Data Index: 8259542 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5319. Min Act: -0.1700
Data Index: 1069088 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5319. Min Act: -0.1700
Data Index: 5870557 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5319. Min Act: -0.1700
Data Index: 612341 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5319. Min Act: -0.1700
Data Index: 5988520 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5319. Min Act: -0.1700
Data Index: 8132900 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5007. Min Act: -0.1700
Data Index: 4152924 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5007. Min Act: -0.1700
Data Index: 3710094 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5007. Min Act: -0.1700
Data Index: 2991001 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5007. Min Act: -0.1700
Data Index: 6699135 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4694. Min Act: -0.1700
Data Index: 4654361 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4694. Min Act: -0.1700
Data Index: 286810 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19