Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1557 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0844. Min Range: -7.0844
Max Act: 7.0844. Min Act: -0.1700
Data Index: 308132 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0844. Min Range: -7.0844
Max Act: 7.0532. Min Act: -0.1700
Data Index: 1712601 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.9594. Min Act: -0.1700
Data Index: 3028188 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.8344. Min Act: -0.1700
Data Index: 1077629 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.8032. Min Act: -0.1700
Data Index: 1081187 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.7719. Min Act: -0.1700
Data Index: 6017537 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.7719. Min Act: -0.1700
Data Index: 7480742 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.7407. Min Act: -0.1700
Data Index: 5894367 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.7407. Min Act: -0.1700
Data Index: 1331191 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.7407. Min Act: -0.1700
Data Index: 8401401 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.7094. Min Act: -0.1700
Data Index: 4316087 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.6469. Min Act: -0.1700
Data Index: 5253353 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.6469. Min Act: -0.1700
Data Index: 2463612 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.6157. Min Act: -0.1700
Data Index: 3674895 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.6157. Min Act: -0.1700
Data Index: 3768313 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.6157. Min Act: -0.1700
Data Index: 3920903 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.5844. Min Act: -0.1700
Data Index: 8176101 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.5844. Min Act: -0.1700
Data Index: 4013826 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.5844. Min Act: -0.1700
Data Index: 2792625 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0844. Min Range: -7.0844
Max Act: 6.5844. Min Act: -0.1700
Data Index: 2130014 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19