Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4187 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5981. Min Act: -0.1700
Data Index: 5793375 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5894. Min Act: -0.1700
Data Index: 1051208 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5806. Min Act: -0.1643
Data Index: 4084603 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5806. Min Act: -0.1485
Data Index: 5275967 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5894. Min Act: -0.1576
Data Index: 4084599 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5806. Min Act: -0.1700
Data Index: 3267996 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5719. Min Act: -0.1698
Data Index: 8673622 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5631. Min Act: -0.1700
Data Index: 8198618 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5544. Min Act: -0.1697
Data Index: 1516612 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5631. Min Act: -0.1520
Data Index: 2525357 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5631. Min Act: -0.1671
Data Index: 1841511 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5631. Min Act: -0.1692
Data Index: 1193166 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5456. Min Act: -0.1624
Data Index: 987638 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5456. Min Act: -0.1514
Data Index: 491145 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5544. Min Act: -0.1566
Data Index: 4453102 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5369. Min Act: -0.1698
Data Index: 4567080 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5369. Min Act: -0.1491
Data Index: 659259 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5369. Min Act: -0.1700
Data Index: 4110741 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5456. Min Act: -0.1696
Data Index: 4594673 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5981. Min Range: -1.5981
Max Act: 1.5369. Min Act: -0.1667
Data Index: 1585111 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19