Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.6569. Min Act: -0.1700
Data Index: 4321333 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.5319. Min Act: -0.1700
Data Index: 178245 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.4069. Min Act: -0.1700
Data Index: 6885786 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.3444. Min Act: -0.1700
Data Index: 4481031 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.3131. Min Act: -0.1700
Data Index: 571319 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.2506. Min Act: -0.1700
Data Index: 1595556 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.2506. Min Act: -0.1700
Data Index: 914571 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.2194. Min Act: -0.1700
Data Index: 475447 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.1569. Min Act: -0.1700
Data Index: 2430714 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.1569. Min Act: -0.1700
Data Index: 7461026 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.1256. Min Act: -0.1700
Data Index: 5321713 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.1256. Min Act: -0.1700
Data Index: 1254137 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.1256. Min Act: -0.1700
Data Index: 1454485 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.0944. Min Act: -0.1700
Data Index: 3730284 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.0631. Min Act: -0.1700
Data Index: 6272553 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.0944. Min Act: -0.1700
Data Index: 6983252 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.0944. Min Act: -0.1700
Data Index: 5607517 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.0944. Min Act: -0.1700
Data Index: 4028269 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.0631. Min Act: -0.1700
Data Index: 3918425 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6569. Min Range: -6.6569
Max Act: 6.0631. Min Act: -0.1700
Data Index: 6318601 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19