Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2517 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1742. Min Range: -4.1742
Max Act: 4.1742. Min Act: -0.1700
Data Index: 6974863 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1742. Min Range: -4.1742
Max Act: 4.0179. Min Act: -0.1700
Data Index: 5878479 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1742. Min Range: -4.1742
Max Act: 4.0179. Min Act: -0.1700
Data Index: 1611404 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.9867. Min Act: -0.1700
Data Index: 3076445 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.9241. Min Act: -0.1700
Data Index: 2786346 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8929. Min Act: -0.1700
Data Index: 4596812 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8616. Min Act: -0.1700
Data Index: 3753 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8616. Min Act: -0.1700
Data Index: 1399325 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8616. Min Act: -0.1700
Data Index: 1217291 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8303. Min Act: -0.1700
Data Index: 2727326 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8303. Min Act: -0.1700
Data Index: 5951836 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8303. Min Act: -0.1700
Data Index: 4438132 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8303. Min Act: -0.1700
Data Index: 5420018 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8303. Min Act: -0.1700
Data Index: 7707398 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.8303. Min Act: -0.1700
Data Index: 4030007 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7678. Min Act: -0.1700
Data Index: 6784474 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7678. Min Act: -0.1700
Data Index: 4326723 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7991. Min Act: -0.1700
Data Index: 7067918 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7991. Min Act: -0.1700
Data Index: 7449151 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1742. Min Range: -4.1742
Max Act: 3.7991. Min Act: -0.1700
Data Index: 2657677 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19