Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 418 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2382. Min Range: -5.2382
Max Act: 5.2382. Min Act: -0.1700
Data Index: 7792027 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2382. Min Range: -5.2382
Max Act: 5.2070. Min Act: -0.1700
Data Index: 4600212 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2382. Min Range: -5.2382
Max Act: 5.1132. Min Act: -0.1700
Data Index: 1904388 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.9882. Min Act: -0.1700
Data Index: 1496909 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.8945. Min Act: -0.1700
Data Index: 8653952 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.7382. Min Act: -0.1700
Data Index: 6035675 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.6445. Min Act: -0.1700
Data Index: 4418285 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.6757. Min Act: -0.1700
Data Index: 1407757 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.6757. Min Act: -0.1700
Data Index: 1148118 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.6445. Min Act: -0.1700
Data Index: 8595125 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.6445. Min Act: -0.1700
Data Index: 862885 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.6445. Min Act: -0.1700
Data Index: 6913412 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.5820. Min Act: -0.1700
Data Index: 740576 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.5820. Min Act: -0.1700
Data Index: 560865 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.5507. Min Act: -0.1700
Data Index: 327502 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.5507. Min Act: -0.1700
Data Index: 5661195 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.5195. Min Act: -0.1700
Data Index: 1128559 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.5195. Min Act: -0.1700
Data Index: 7974426 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.5195. Min Act: -0.1700
Data Index: 1747022 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2382. Min Range: -5.2382
Max Act: 4.4882. Min Act: -0.1700
Data Index: 7718380 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19