Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1604 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.3279. Min Act: -0.1700
Data Index: 8228098 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2654. Min Act: -0.1700
Data Index: 6792039 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2654. Min Act: -0.1699
Data Index: 2965586 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2654. Min Act: -0.1700
Data Index: 4464013 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2342. Min Act: -0.1700
Data Index: 1469363 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2342. Min Act: -0.1700
Data Index: 1134736 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2342. Min Act: -0.1700
Data Index: 4739081 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2342. Min Act: -0.1700
Data Index: 4375370 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2342. Min Act: -0.1700
Data Index: 2836526 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2342. Min Act: -0.1700
Data Index: 563133 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2029. Min Act: -0.1700
Data Index: 6318526 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2029. Min Act: -0.1700
Data Index: 420094 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2029. Min Act: -0.1700
Data Index: 6386766 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.2029. Min Act: -0.1700
Data Index: 7508349 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1069155 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.1717. Min Act: -0.1700
Data Index: 2926308 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.1717. Min Act: -0.1700
Data Index: 849815 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1799001 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.1404. Min Act: -0.1700
Data Index: 6381093 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3279. Min Range: -5.3279
Max Act: 5.1717. Min Act: -0.1700
Data Index: 6386764 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19