Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.8598. Min Act: -0.1700
Data Index: 7518208 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.8598. Min Act: -0.1700
Data Index: 6615064 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.7973. Min Act: -0.1700
Data Index: 4633451 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.7660. Min Act: -0.1700
Data Index: 4528321 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.7660. Min Act: -0.1700
Data Index: 7616167 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.6723. Min Act: -0.1700
Data Index: 6880343 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.6723. Min Act: -0.1700
Data Index: 1349627 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.6410. Min Act: -0.1700
Data Index: 1471603 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5785. Min Act: -0.1700
Data Index: 7107907 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5785. Min Act: -0.1700
Data Index: 3035061 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5785. Min Act: -0.1700
Data Index: 5808994 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5785. Min Act: -0.1700
Data Index: 5761182 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5785. Min Act: -0.1700
Data Index: 4857511 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5785. Min Act: -0.1700
Data Index: 609426 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5473. Min Act: -0.1700
Data Index: 2732199 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5473. Min Act: -0.1700
Data Index: 7165208 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5160. Min Act: -0.1700
Data Index: 3753654 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5160. Min Act: -0.1700
Data Index: 8030698 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.5160. Min Act: -0.1700
Data Index: 915960 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8598. Min Range: -6.8598
Max Act: 6.4848. Min Act: -0.1700
Data Index: 4150693 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19