Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1424. Min Range: -6.1424
Max Act: 6.1424. Min Act: -0.1700
Data Index: 3767357 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.9549. Min Act: -0.1700
Data Index: 7363544 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.9237. Min Act: -0.1700
Data Index: 1380279 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.8612. Min Act: -0.1700
Data Index: 1345946 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.8612. Min Act: -0.1700
Data Index: 3376981 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7987. Min Act: -0.1700
Data Index: 669130 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7987. Min Act: -0.1700
Data Index: 2472365 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7362. Min Act: -0.1700
Data Index: 1290650 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7362. Min Act: -0.1700
Data Index: 6145437 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7362. Min Act: -0.1700
Data Index: 6367565 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7049. Min Act: -0.1700
Data Index: 3172094 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7049. Min Act: -0.1700
Data Index: 4661420 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7049. Min Act: -0.1700
Data Index: 8543739 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.6737. Min Act: -0.1700
Data Index: 221630 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.7049. Min Act: -0.1700
Data Index: 756020 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.6737. Min Act: -0.1700
Data Index: 943274 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.6424. Min Act: -0.1700
Data Index: 8565585 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.6737. Min Act: -0.1700
Data Index: 8228274 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.6424. Min Act: -0.1700
Data Index: 2200970 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1424. Min Range: -6.1424
Max Act: 5.6424. Min Act: -0.1700
Data Index: 2311838 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19