Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0510. Min Range: -8.0510
Max Act: 8.0510. Min Act: -0.1700
Data Index: 4801509 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.8635. Min Act: -0.1700
Data Index: 1318337 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.7385. Min Act: -0.1700
Data Index: 6521008 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.6135. Min Act: -0.1700
Data Index: 6080800 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.5510. Min Act: -0.1700
Data Index: 257956 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 2566303 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3948. Min Act: -0.1700
Data Index: 2363135 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3948. Min Act: -0.1700
Data Index: 8597524 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 648882 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3010. Min Act: -0.1700
Data Index: 8057416 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2698. Min Act: -0.1700
Data Index: 5060063 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.3010. Min Act: -0.1700
Data Index: 7025725 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2385. Min Act: -0.1700
Data Index: 5573714 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2385. Min Act: -0.1700
Data Index: 5992404 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2385. Min Act: -0.1700
Data Index: 2480586 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.2073. Min Act: -0.1700
Data Index: 133426 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.1760. Min Act: -0.1700
Data Index: 1403922 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.1760. Min Act: -0.1700
Data Index: 8594040 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.1760. Min Act: -0.1700
Data Index: 7921956 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0510. Min Range: -8.0510
Max Act: 7.1760. Min Act: -0.1700
Data Index: 3714949 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19