Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.7542. Min Act: -0.1700
Data Index: 6850032 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.6292. Min Act: -0.1700
Data Index: 1559397 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.5667. Min Act: -0.1700
Data Index: 1028792 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.4417. Min Act: -0.1700
Data Index: 2491673 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.4417. Min Act: -0.1700
Data Index: 5323909 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.3792. Min Act: -0.1700
Data Index: 8588029 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.3167. Min Act: -0.1700
Data Index: 3193245 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.2542. Min Act: -0.1700
Data Index: 7134334 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.2542. Min Act: -0.1700
Data Index: 332596 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.1917. Min Act: -0.1700
Data Index: 3446911 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.1292. Min Act: -0.1700
Data Index: 857091 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.1292. Min Act: -0.1700
Data Index: 1922386 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.1292. Min Act: -0.1700
Data Index: 6048545 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.1292. Min Act: -0.1700
Data Index: 1627420 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.1917. Min Act: -0.1700
Data Index: 5689153 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.1917. Min Act: -0.1700
Data Index: 8186783 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.0667. Min Act: -0.1700
Data Index: 7269241 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.0667. Min Act: -0.1700
Data Index: 1296649 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.0667. Min Act: -0.1700
Data Index: 5866323 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7542. Min Range: -8.7542
Max Act: 8.0042. Min Act: -0.1700
Data Index: 1842157 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19