Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.9627. Min Act: -0.1700
Data Index: 6806426 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.9315. Min Act: -0.1700
Data Index: 7133684 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.8065. Min Act: -0.1700
Data Index: 4517042 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.8065. Min Act: -0.1700
Data Index: 1128126 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.7440. Min Act: -0.1700
Data Index: 7573625 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.7127. Min Act: -0.1700
Data Index: 8273307 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.7127. Min Act: -0.1700
Data Index: 1149064 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.7127. Min Act: -0.1700
Data Index: 5184998 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.6190. Min Act: -0.1700
Data Index: 2939644 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.5877. Min Act: -0.1700
Data Index: 1699712 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.6190. Min Act: -0.1700
Data Index: 1901155 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.5565. Min Act: -0.1700
Data Index: 6678313 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.5565. Min Act: -0.1700
Data Index: 2748847 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.5565. Min Act: -0.1700
Data Index: 7130720 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.4940. Min Act: -0.1700
Data Index: 487342 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.4940. Min Act: -0.1700
Data Index: 4120681 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.5252. Min Act: -0.1700
Data Index: 8046213 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.4940. Min Act: -0.1700
Data Index: 1219460 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.4627. Min Act: -0.1700
Data Index: 2261401 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9627. Min Range: -6.9627
Max Act: 6.4315. Min Act: -0.1700
Data Index: 4504675 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19