Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5341 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.9432. Min Act: -0.1700
Data Index: 6757227 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.8321. Min Act: -0.1700
Data Index: 6757228 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7844. Min Act: -0.1700
Data Index: 4862593 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7844. Min Act: -0.1700
Data Index: 7176750 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7684. Min Act: -0.1700
Data Index: 5858107 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7525. Min Act: -0.1700
Data Index: 6792535 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7684. Min Act: -0.1700
Data Index: 5039066 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7365. Min Act: -0.1700
Data Index: 4685261 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7205. Min Act: -0.1700
Data Index: 7622777 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7045. Min Act: -0.1700
Data Index: 6341965 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7045. Min Act: -0.1700
Data Index: 670096 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6885. Min Act: -0.1700
Data Index: 102227 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6885. Min Act: -0.1700
Data Index: 4350057 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6725. Min Act: -0.1700
Data Index: 2830329 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6885. Min Act: -0.1700
Data Index: 7354578 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6885. Min Act: -0.1700
Data Index: 2647506 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.7045. Min Act: -0.1700
Data Index: 3271179 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6885. Min Act: -0.1700
Data Index: 5048597 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6725. Min Act: -0.1700
Data Index: 3190368 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9432. Min Range: -2.9432
Max Act: 2.6565. Min Act: -0.1700
Data Index: 3708342 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19