Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0385. Min Range: -10.0385
Max Act: 10.0385. Min Act: -0.1700
Data Index: 61755 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.9760. Min Act: -0.1700
Data Index: 4079171 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.8510. Min Act: -0.1700
Data Index: 8364797 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.4760. Min Act: -0.1700
Data Index: 8026147 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.4135. Min Act: -0.1700
Data Index: 8356819 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.3510. Min Act: -0.1700
Data Index: 6727017 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.2260. Min Act: -0.1700
Data Index: 2247501 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.1635. Min Act: -0.1700
Data Index: 858860 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.1010. Min Act: -0.1700
Data Index: 7500037 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.0385. Min Act: -0.1700
Data Index: 8364799 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.0385. Min Act: -0.1700
Data Index: 2065645 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0385. Min Range: -10.0385
Max Act: 9.1010. Min Act: -0.1700
Data Index: 4641331 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.9760. Min Act: -0.1700
Data Index: 2797688 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.9135. Min Act: -0.1700
Data Index: 2401452 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.8510. Min Act: -0.1700
Data Index: 7438297 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.8510. Min Act: -0.1700
Data Index: 5677018 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.7885. Min Act: -0.1700
Data Index: 2767802 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.7260. Min Act: -0.1700
Data Index: 4401762 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.7260. Min Act: -0.1700
Data Index: 4620047 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0385. Min Range: -10.0385
Max Act: 8.7260. Min Act: -0.1700
Data Index: 2316081 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19