Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.6196. Min Act: -0.1700
Data Index: 4939159 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.3696. Min Act: -0.1700
Data Index: 3808682 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.3071. Min Act: -0.1700
Data Index: 1073228 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.2758. Min Act: -0.1700
Data Index: 5217757 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.2133. Min Act: -0.1700
Data Index: 409348 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.2133. Min Act: -0.1700
Data Index: 7013374 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.1508. Min Act: -0.1700
Data Index: 2930226 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.1508. Min Act: -0.1700
Data Index: 382447 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.0883. Min Act: -0.1700
Data Index: 7558021 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.0571. Min Act: -0.1700
Data Index: 8724539 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.0571. Min Act: -0.1700
Data Index: 6422443 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9946. Min Act: -0.1700
Data Index: 147893 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6196. Min Range: -5.6196
Max Act: 5.0571. Min Act: -0.1700
Data Index: 5509705 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9946. Min Act: -0.1700
Data Index: 5960886 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9633. Min Act: -0.1700
Data Index: 6542004 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9633. Min Act: -0.1700
Data Index: 5424152 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9321. Min Act: -0.1700
Data Index: 7123258 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9321. Min Act: -0.1700
Data Index: 5581413 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9008. Min Act: -0.1700
Data Index: 3371931 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6196. Min Range: -5.6196
Max Act: 4.9321. Min Act: -0.1700
Data Index: 6061010 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19