Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1998 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.5390. Min Act: -0.1700
Data Index: 4022223 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.4765. Min Act: -0.1700
Data Index: 6701060 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.4140. Min Act: -0.1700
Data Index: 4022224 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.3827. Min Act: -0.1700
Data Index: 687311 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.3202. Min Act: -0.1700
Data Index: 6226705 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.3514. Min Act: -0.1700
Data Index: 6226706 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.2889. Min Act: -0.1700
Data Index: 8699661 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.2577. Min Act: -0.1700
Data Index: 8587782 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1952. Min Act: -0.1700
Data Index: 8231340 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1952. Min Act: -0.1700
Data Index: 3276206 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1639. Min Act: -0.1700
Data Index: 1796994 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1014. Min Act: -0.1700
Data Index: 1796989 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1014. Min Act: -0.1700
Data Index: 3045602 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1014. Min Act: -0.1700
Data Index: 6480141 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1014. Min Act: -0.1700
Data Index: 4703453 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1014. Min Act: -0.1700
Data Index: 6980214 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.1014. Min Act: -0.1700
Data Index: 1378763 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.0702. Min Act: -0.1700
Data Index: 7599406 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.0702. Min Act: -0.1700
Data Index: 2534412 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5390. Min Range: -4.5390
Max Act: 4.0702. Min Act: -0.1700
Data Index: 3276207 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19