Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.9569. Min Act: -0.1700
Data Index: 2136318 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.7069. Min Act: -0.1700
Data Index: 706446 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.6444. Min Act: -0.1700
Data Index: 1840585 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.5819. Min Act: -0.1700
Data Index: 27742 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.5194. Min Act: -0.1700
Data Index: 8324418 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.4569. Min Act: -0.1700
Data Index: 804391 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.4569. Min Act: -0.1700
Data Index: 1324563 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.4569. Min Act: -0.1700
Data Index: 600566 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3632. Min Act: -0.1700
Data Index: 4986039 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3944. Min Act: -0.1700
Data Index: 568763 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3944. Min Act: -0.1700
Data Index: 1560803 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3944. Min Act: -0.1700
Data Index: 7298341 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3944. Min Act: -0.1700
Data Index: 829966 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3632. Min Act: -0.1700
Data Index: 852349 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3632. Min Act: -0.1700
Data Index: 833329 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3319. Min Act: -0.1700
Data Index: 8816065 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3007. Min Act: -0.1700
Data Index: 892543 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3319. Min Act: -0.1700
Data Index: 4282807 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3319. Min Act: -0.1700
Data Index: 800254 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9569. Min Range: -7.9569
Max Act: 7.3319. Min Act: -0.1700
Data Index: 1482930 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19