Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.7599. Min Act: -0.1700
Data Index: 7909223 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.4474. Min Act: -0.1700
Data Index: 6520444 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.2599. Min Act: -0.1700
Data Index: 2608578 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.1661. Min Act: -0.1700
Data Index: 6491732 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.1661. Min Act: -0.1700
Data Index: 1977222 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.1661. Min Act: -0.1700
Data Index: 2548717 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.1349. Min Act: -0.1700
Data Index: 4418539 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.0724. Min Act: -0.1700
Data Index: 146172 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.0411. Min Act: -0.1700
Data Index: 3345628 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.0724. Min Act: -0.1700
Data Index: 4973508 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.0411. Min Act: -0.1700
Data Index: 6485410 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.0411. Min Act: -0.1700
Data Index: 6001786 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7599. Min Range: -7.7599
Max Act: 7.0099. Min Act: -0.1700
Data Index: 1582738 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7599. Min Range: -7.7599
Max Act: 6.9786. Min Act: -0.1700
Data Index: 16454 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7599. Min Range: -7.7599
Max Act: 6.9474. Min Act: -0.1700
Data Index: 8211553 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7599. Min Range: -7.7599
Max Act: 6.9474. Min Act: -0.1700
Data Index: 8401234 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7599. Min Range: -7.7599
Max Act: 6.9161. Min Act: -0.1700
Data Index: 4082410 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7599. Min Range: -7.7599
Max Act: 6.9161. Min Act: -0.1700
Data Index: 3118391 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7599. Min Range: -7.7599
Max Act: 6.9161. Min Act: -0.1700
Data Index: 4088439 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7599. Min Range: -7.7599
Max Act: 6.9161. Min Act: -0.1700
Data Index: 5237612 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19