Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.6817. Min Act: -0.1700
Data Index: 236657 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.6504. Min Act: -0.1700
Data Index: 1287898 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.6504. Min Act: -0.1700
Data Index: 5444131 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.5879. Min Act: -0.1700
Data Index: 4790343 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.5879. Min Act: -0.1700
Data Index: 4977441 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.5567. Min Act: -0.1700
Data Index: 8769578 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4942. Min Act: -0.1700
Data Index: 7026111 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4942. Min Act: -0.1700
Data Index: 8693802 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4942. Min Act: -0.1700
Data Index: 4924035 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4629. Min Act: -0.1700
Data Index: 8397767 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4629. Min Act: -0.1700
Data Index: 966092 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4629. Min Act: -0.1700
Data Index: 1861559 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4629. Min Act: -0.1700
Data Index: 4103714 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4004. Min Act: -0.1700
Data Index: 147292 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.4004. Min Act: -0.1700
Data Index: 5395942 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.3379. Min Act: -0.1700
Data Index: 772183 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.3692. Min Act: -0.1700
Data Index: 5318707 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.3692. Min Act: -0.1700
Data Index: 8413300 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.3692. Min Act: -0.1700
Data Index: 6760705 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6817. Min Range: -5.6817
Max Act: 5.3379. Min Act: -0.1700
Data Index: 6502944 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19