Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 973 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.5243. Min Act: -0.1700
Data Index: 1182238 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.3993. Min Act: -0.1700
Data Index: 7216616 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.3681. Min Act: -0.1700
Data Index: 6282621 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.3056. Min Act: -0.1700
Data Index: 5800105 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.2743. Min Act: -0.1700
Data Index: 2112696 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.2431. Min Act: -0.1700
Data Index: 862498 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.1806. Min Act: -0.1700
Data Index: 7159152 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.1493. Min Act: -0.1700
Data Index: 3944795 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.1493. Min Act: -0.1700
Data Index: 5973033 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1662423 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.1181. Min Act: -0.1700
Data Index: 5808056 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.1181. Min Act: -0.1700
Data Index: 8526824 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.0868. Min Act: -0.1700
Data Index: 1081201 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.0556. Min Act: -0.1700
Data Index: 2951350 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.0556. Min Act: -0.1700
Data Index: 7712671 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.0556. Min Act: -0.1700
Data Index: 2218288 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5243. Min Range: -6.5243
Max Act: 5.9931. Min Act: -0.1700
Data Index: 4909066 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.0243. Min Act: -0.1700
Data Index: 8288656 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5243. Min Range: -6.5243
Max Act: 6.0243. Min Act: -0.1700
Data Index: 8207454 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5243. Min Range: -6.5243
Max Act: 5.9618. Min Act: -0.1700
Data Index: 4532337 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19