Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1340 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.9660. Min Act: -0.1700
Data Index: 794633 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.7472. Min Act: -0.1700
Data Index: 7372362 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4972. Min Act: -0.1700
Data Index: 6361900 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4972. Min Act: -0.1700
Data Index: 3787580 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4972. Min Act: -0.1700
Data Index: 7280392 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4660. Min Act: -0.1700
Data Index: 2450974 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4347. Min Act: -0.1700
Data Index: 1525334 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4035. Min Act: -0.1700
Data Index: 6900456 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.4035. Min Act: -0.1700
Data Index: 544201 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.3722. Min Act: -0.1700
Data Index: 666972 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.3410. Min Act: -0.1700
Data Index: 544197 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.3097. Min Act: -0.1700
Data Index: 4101514 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2785. Min Act: -0.1700
Data Index: 4894646 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2785. Min Act: -0.1700
Data Index: 8471035 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2472. Min Act: -0.1700
Data Index: 877133 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2472. Min Act: -0.1700
Data Index: 6118377 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 7745389 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 1753682 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 1569581 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9660. Min Range: -6.9660
Max Act: 6.2160. Min Act: -0.1700
Data Index: 8256180 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19