Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.8807. Min Act: -0.1700
Data Index: 5819377 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.8181. Min Act: -0.1700
Data Index: 8411347 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6930. Min Act: -0.1700
Data Index: 6880873 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6617. Min Act: -0.1700
Data Index: 4866693 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6461. Min Act: -0.1700
Data Index: 6142415 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6304. Min Act: -0.1700
Data Index: 6170763 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6617. Min Act: -0.1700
Data Index: 6243892 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6461. Min Act: -0.1700
Data Index: 985864 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6461. Min Act: -0.1700
Data Index: 6681029 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6461. Min Act: -0.1700
Data Index: 315869 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6304. Min Act: -0.1700
Data Index: 2950779 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6148. Min Act: -0.1700
Data Index: 6761561 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6148. Min Act: -0.1700
Data Index: 4441943 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6148. Min Act: -0.1700
Data Index: 5904297 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6148. Min Act: -0.1700
Data Index: 6626169 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6148. Min Act: -0.1700
Data Index: 4446022 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6148. Min Act: -0.1700
Data Index: 6611617 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.6148. Min Act: -0.1700
Data Index: 7001864 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.5991. Min Act: -0.1700
Data Index: 6636700 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8807. Min Range: -3.8807
Max Act: 3.5991. Min Act: -0.1700
Data Index: 4450217 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19