Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.5451. Min Act: -0.1700
Data Index: 2677540 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.4826. Min Act: -0.1700
Data Index: 6781991 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0763. Min Act: -0.1700
Data Index: 7748205 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 5129962 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0138. Min Act: -0.1700
Data Index: 6273411 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.9826. Min Act: -0.1700
Data Index: 4518404 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0138. Min Act: -0.1700
Data Index: 4636416 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.9513. Min Act: -0.1700
Data Index: 6338901 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.9201. Min Act: -0.1700
Data Index: 2930505 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.8888. Min Act: -0.1700
Data Index: 362276 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.9513. Min Act: -0.1700
Data Index: 2230884 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.9201. Min Act: -0.1700
Data Index: 6066834 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.9201. Min Act: -0.1700
Data Index: 2841141 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.8888. Min Act: -0.1700
Data Index: 1476549 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.8888. Min Act: -0.1700
Data Index: 3910523 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.8576. Min Act: -0.1700
Data Index: 4764375 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.8263. Min Act: -0.1700
Data Index: 5671776 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.7951. Min Act: -0.1700
Data Index: 759806 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.7951. Min Act: -0.1700
Data Index: 6464926 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.7951. Min Act: -0.1700
Data Index: 4777822 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19