Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5777 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1292. Min Range: -5.1292
Max Act: 5.1292. Min Act: -0.1700
Data Index: 2868753 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1292. Min Range: -5.1292
Max Act: 5.1292. Min Act: -0.1700
Data Index: 6146697 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1292. Min Range: -5.1292
Max Act: 5.0667. Min Act: -0.1700
Data Index: 2868747 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.9417. Min Act: -0.1700
Data Index: 6857336 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.8480. Min Act: -0.1700
Data Index: 6738386 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.8792. Min Act: -0.1700
Data Index: 4951506 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.8480. Min Act: -0.1700
Data Index: 8607190 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.8167. Min Act: -0.1700
Data Index: 5877279 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.8167. Min Act: -0.1700
Data Index: 4524546 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.7855. Min Act: -0.1700
Data Index: 3093547 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.7855. Min Act: -0.1700
Data Index: 1797181 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.8167. Min Act: -0.1700
Data Index: 2143513 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.7542. Min Act: -0.1700
Data Index: 669080 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.7230. Min Act: -0.1700
Data Index: 5401174 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.6917. Min Act: -0.1700
Data Index: 6631222 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.6605. Min Act: -0.1700
Data Index: 7651598 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.6605. Min Act: -0.1700
Data Index: 7651037 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.6605. Min Act: -0.1700
Data Index: 2020523 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.6292. Min Act: -0.1700
Data Index: 3822082 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1292. Min Range: -5.1292
Max Act: 4.6605. Min Act: -0.1700
Data Index: 7432186 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19