Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 429 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.9279. Min Act: -0.1700
Data Index: 8148812 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.9109. Min Act: -0.1700
Data Index: 1937586 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.9109. Min Act: -0.1700
Data Index: 4925198 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.8254. Min Act: -0.1700
Data Index: 2564585 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.8254. Min Act: -0.1700
Data Index: 259166 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.8254. Min Act: -0.1700
Data Index: 8780034 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.8082. Min Act: -0.1700
Data Index: 2715281 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.8082. Min Act: -0.1700
Data Index: 6669789 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.8082. Min Act: -0.1700
Data Index: 1567181 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7737. Min Act: -0.1700
Data Index: 3249047 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7737. Min Act: -0.1700
Data Index: 5074623 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7737. Min Act: -0.1700
Data Index: 1046578 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7737. Min Act: -0.1700
Data Index: 2564099 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7392. Min Act: -0.1700
Data Index: 4189159 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7565. Min Act: -0.1700
Data Index: 1708976 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7392. Min Act: -0.1700
Data Index: 3620452 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7565. Min Act: -0.1700
Data Index: 3441312 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7392. Min Act: -0.1700
Data Index: 2858726 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7392. Min Act: -0.1700
Data Index: 6905340 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9279. Min Range: -1.9279
Max Act: 1.7219. Min Act: -0.1700
Data Index: 2286813 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19