Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.9973. Min Act: -0.1700
Data Index: 711537 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.9348. Min Act: -0.1700
Data Index: 548395 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.9035. Min Act: -0.1700
Data Index: 2695824 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.8410. Min Act: -0.1700
Data Index: 3942262 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.8098. Min Act: -0.1700
Data Index: 3942252 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.8098. Min Act: -0.1700
Data Index: 256004 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.7785. Min Act: -0.1700
Data Index: 1990865 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.7473. Min Act: -0.1700
Data Index: 4097127 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.7473. Min Act: -0.1700
Data Index: 711540 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.7160. Min Act: -0.1700
Data Index: 238297 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.7160. Min Act: -0.1700
Data Index: 3856032 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.7160. Min Act: -0.1700
Data Index: 6752442 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6848. Min Act: -0.1700
Data Index: 6127680 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6848. Min Act: -0.1700
Data Index: 4389626 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6535. Min Act: -0.1700
Data Index: 3454241 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7034383 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6223. Min Act: -0.1700
Data Index: 2510035 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6223. Min Act: -0.1700
Data Index: 6262219 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6223. Min Act: -0.1700
Data Index: 7032792 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9973. Min Range: -5.9973
Max Act: 5.6223. Min Act: -0.1700
Data Index: 1433480 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19