Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4307 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0061. Min Range: -4.0061
Max Act: 4.0061. Min Act: -0.1700
Data Index: 5185715 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9749. Min Act: -0.1700
Data Index: 3521508 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9749. Min Act: -0.1700
Data Index: 3687311 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9436. Min Act: -0.1700
Data Index: 7782090 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9124. Min Act: -0.1700
Data Index: 2371430 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8967. Min Act: -0.1700
Data Index: 7782081 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9124. Min Act: -0.1700
Data Index: 3834279 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8967. Min Act: -0.1700
Data Index: 7240825 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8967. Min Act: -0.1700
Data Index: 5363700 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8811. Min Act: -0.1700
Data Index: 7500863 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8655. Min Act: -0.1700
Data Index: 3510435 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8498. Min Act: -0.1700
Data Index: 5009550 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8655. Min Act: -0.1700
Data Index: 3386768 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8342. Min Act: -0.1700
Data Index: 1106606 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8342. Min Act: -0.1700
Data Index: 6671931 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8342. Min Act: -0.1700
Data Index: 4571730 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8342. Min Act: -0.1700
Data Index: 5457677 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8186. Min Act: -0.1700
Data Index: 2932496 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8186. Min Act: -0.1700
Data Index: 6330586 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8029. Min Act: -0.1700
Data Index: 5759282 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19