Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.4846. Min Act: -0.1700
Data Index: 1443901 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.3283. Min Act: -0.1700
Data Index: 7001583 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.2033. Min Act: -0.1700
Data Index: 4272220 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1721. Min Act: -0.1700
Data Index: 7635053 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1721. Min Act: -0.1700
Data Index: 5434632 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.2033. Min Act: -0.1700
Data Index: 2500822 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1096. Min Act: -0.1700
Data Index: 2939318 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1408. Min Act: -0.1700
Data Index: 2201569 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1408. Min Act: -0.1700
Data Index: 5540724 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1096. Min Act: -0.1700
Data Index: 2074377 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1096. Min Act: -0.1700
Data Index: 2580607 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1096. Min Act: -0.1700
Data Index: 2201568 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.1096. Min Act: -0.1700
Data Index: 2939321 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.0783. Min Act: -0.1700
Data Index: 6980606 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.0471. Min Act: -0.1700
Data Index: 4875124 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.0471. Min Act: -0.1700
Data Index: 2201570 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.0471. Min Act: -0.1700
Data Index: 2201566 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.0471. Min Act: -0.1700
Data Index: 5209023 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.0471. Min Act: -0.1700
Data Index: 7793727 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4846. Min Range: -6.4846
Max Act: 6.0158. Min Act: -0.1700
Data Index: 2023851 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19