Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 938 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.6504. Min Act: -0.1671
Data Index: 700086 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.6504. Min Act: -0.1695
Data Index: 6320598 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.5566. Min Act: -0.1693
Data Index: 2018634 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.5566. Min Act: -0.1646
Data Index: 5770724 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.5254. Min Act: -0.1698
Data Index: 509291 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.4004. Min Act: -0.1695
Data Index: 4520645 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.4004. Min Act: -0.1700
Data Index: 2476894 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3691. Min Act: -0.1700
Data Index: 2500411 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3691. Min Act: -0.1700
Data Index: 6655607 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3691. Min Act: -0.1700
Data Index: 4855260 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3691. Min Act: -0.1700
Data Index: 5217712 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3379. Min Act: -0.1684
Data Index: 3607795 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3379. Min Act: -0.1678
Data Index: 5329156 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.2754. Min Act: -0.1700
Data Index: 467307 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3066. Min Act: -0.1699
Data Index: 899273 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.2754. Min Act: -0.1700
Data Index: 6037293 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3066. Min Act: -0.1699
Data Index: 8007412 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3066. Min Act: -0.1700
Data Index: 8789518 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.3066. Min Act: -0.1700
Data Index: 6409148 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6504. Min Range: -6.6504
Max Act: 6.2754. Min Act: -0.1685
Data Index: 916711 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19