Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4474. Min Range: -8.4474
Max Act: 8.4474. Min Act: -0.1700
Data Index: 816021 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4474. Min Range: -8.4474
Max Act: 8.3849. Min Act: -0.1700
Data Index: 816020 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4474. Min Range: -8.4474
Max Act: 8.0724. Min Act: -0.1700
Data Index: 6232587 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.8849. Min Act: -0.1700
Data Index: 4651874 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.7599. Min Act: -0.1700
Data Index: 399012 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.6974. Min Act: -0.1700
Data Index: 7871662 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.6662. Min Act: -0.1700
Data Index: 4755476 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.6349. Min Act: -0.1700
Data Index: 7256606 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.6037. Min Act: -0.1700
Data Index: 906845 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.5412. Min Act: -0.1700
Data Index: 3020057 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.5099. Min Act: -0.1700
Data Index: 816019 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.5099. Min Act: -0.1700
Data Index: 2616738 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.5099. Min Act: -0.1700
Data Index: 1012111 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.5099. Min Act: -0.1700
Data Index: 2781146 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.5099. Min Act: -0.1700
Data Index: 137489 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.4162. Min Act: -0.1700
Data Index: 8663003 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.4162. Min Act: -0.1700
Data Index: 1952159 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.3849. Min Act: -0.1700
Data Index: 6740523 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.3849. Min Act: -0.1700
Data Index: 814852 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4474. Min Range: -8.4474
Max Act: 7.3849. Min Act: -0.1700
Data Index: 6925586 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19