Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2588. Min Range: -7.2588
Max Act: 7.2588. Min Act: -0.1700
Data Index: 1364637 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2588. Min Range: -7.2588
Max Act: 7.2275. Min Act: -0.1700
Data Index: 3251973 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2588. Min Range: -7.2588
Max Act: 7.1963. Min Act: -0.1700
Data Index: 8361033 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2588. Min Range: -7.2588
Max Act: 7.1963. Min Act: -0.1700
Data Index: 3873381 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2588. Min Range: -7.2588
Max Act: 7.1338. Min Act: -0.1700
Data Index: 3584846 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2588. Min Range: -7.2588
Max Act: 7.0713. Min Act: -0.1700
Data Index: 3251974 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2588. Min Range: -7.2588
Max Act: 7.0088. Min Act: -0.1700
Data Index: 1040467 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.9775. Min Act: -0.1700
Data Index: 6238592 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.9463. Min Act: -0.1700
Data Index: 3251972 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.9150. Min Act: -0.1700
Data Index: 3912927 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.9150. Min Act: -0.1700
Data Index: 8141625 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.8838. Min Act: -0.1700
Data Index: 4578404 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.8525. Min Act: -0.1700
Data Index: 61937 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.8213. Min Act: -0.1700
Data Index: 4913261 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.8213. Min Act: -0.1700
Data Index: 4578405 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.8213. Min Act: -0.1700
Data Index: 1489204 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.8213. Min Act: -0.1700
Data Index: 2112672 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.7588. Min Act: -0.1700
Data Index: 5901269 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.8213. Min Act: -0.1700
Data Index: 1580311 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2588. Min Range: -7.2588
Max Act: 6.7900. Min Act: -0.1700
Data Index: 5928653 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19