Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.9382. Min Act: -0.1700
Data Index: 6514676 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.9382. Min Act: -0.1700
Data Index: 3619206 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8757. Min Act: -0.1700
Data Index: 4895951 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8444. Min Act: -0.1699
Data Index: 3036316 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8444. Min Act: -0.1694
Data Index: 558652 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8444. Min Act: -0.1700
Data Index: 2438846 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 1169221 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.7819. Min Act: -0.1700
Data Index: 2573604 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 735658 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 2540646 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 2438844 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 594218 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 891896 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 8671913 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.8132. Min Act: -0.1700
Data Index: 8508139 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.7819. Min Act: -0.1700
Data Index: 4572064 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.7819. Min Act: -0.1700
Data Index: 149571 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.7819. Min Act: -0.1700
Data Index: 4033556 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.7819. Min Act: -0.1700
Data Index: 3362371 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9382. Min Range: -4.9382
Max Act: 4.7819. Min Act: -0.1700
Data Index: 5405013 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19