Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4956 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2346. Min Range: -6.2346
Max Act: 6.2346. Min Act: -0.1700
Data Index: 790621 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2346. Min Range: -6.2346
Max Act: 6.1096. Min Act: -0.1700
Data Index: 6026765 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2346. Min Range: -6.2346
Max Act: 6.0783. Min Act: -0.1700
Data Index: 898533 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2346. Min Range: -6.2346
Max Act: 6.0158. Min Act: -0.1700
Data Index: 613140 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9846. Min Act: -0.1700
Data Index: 8322305 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9846. Min Act: -0.1700
Data Index: 106363 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9533. Min Act: -0.1700
Data Index: 1739390 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9533. Min Act: -0.1700
Data Index: 8460265 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9533. Min Act: -0.1700
Data Index: 440541 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9533. Min Act: -0.1700
Data Index: 497826 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9533. Min Act: -0.1700
Data Index: 3038555 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9221. Min Act: -0.1700
Data Index: 3945501 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6078420 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9221. Min Act: -0.1700
Data Index: 3119601 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9221. Min Act: -0.1700
Data Index: 7745105 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.9533. Min Act: -0.1700
Data Index: 4066259 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.8908. Min Act: -0.1700
Data Index: 3153303 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.8596. Min Act: -0.1700
Data Index: 2113487 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.8908. Min Act: -0.1700
Data Index: 5439105 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2346. Min Range: -6.2346
Max Act: 5.8908. Min Act: -0.1700
Data Index: 3481529 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19