Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6997. Min Range: -6.6997
Max Act: 6.6997. Min Act: -0.1700
Data Index: 6107588 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.9185. Min Act: -0.1700
Data Index: 7355312 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.8872. Min Act: -0.1700
Data Index: 4659688 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.8560. Min Act: -0.1700
Data Index: 1170259 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.7935. Min Act: -0.1700
Data Index: 8122062 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.7622. Min Act: -0.1700
Data Index: 2168840 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.7622. Min Act: -0.1700
Data Index: 704544 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.7310. Min Act: -0.1700
Data Index: 2546672 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.7310. Min Act: -0.1700
Data Index: 4591669 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.6997. Min Act: -0.1700
Data Index: 7152678 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.6685. Min Act: -0.1700
Data Index: 5096834 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.6372. Min Act: -0.1700
Data Index: 2805812 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.6685. Min Act: -0.1700
Data Index: 4452168 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.6060. Min Act: -0.1700
Data Index: 4485239 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.6060. Min Act: -0.1700
Data Index: 6427243 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.5747. Min Act: -0.1700
Data Index: 2360232 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.6060. Min Act: -0.1700
Data Index: 148997 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.5435. Min Act: -0.1700
Data Index: 4429344 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.5122. Min Act: -0.1700
Data Index: 1347333 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6997. Min Range: -6.6997
Max Act: 5.5122. Min Act: -0.1700
Data Index: 6935403 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19