Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.8234. Min Act: -0.1700
Data Index: 2140689 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.6984. Min Act: -0.1700
Data Index: 400298 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.6359. Min Act: -0.1700
Data Index: 2044226 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5734. Min Act: -0.1700
Data Index: 5089983 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5734. Min Act: -0.1700
Data Index: 578477 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.4484. Min Act: -0.1700
Data Index: 1890615 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5109. Min Act: -0.1700
Data Index: 2104957 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5109. Min Act: -0.1700
Data Index: 645154 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5109. Min Act: -0.1700
Data Index: 8287485 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5109. Min Act: -0.1700
Data Index: 5509619 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5109. Min Act: -0.1700
Data Index: 5089161 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5109. Min Act: -0.1700
Data Index: 2570446 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.5109. Min Act: -0.1700
Data Index: 2335050 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.4484. Min Act: -0.1700
Data Index: 6858342 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.4484. Min Act: -0.1700
Data Index: 2265651 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.4484. Min Act: -0.1700
Data Index: 2615661 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.4484. Min Act: -0.1700
Data Index: 6785524 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.4484. Min Act: -0.1700
Data Index: 8760511 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.4484. Min Act: -0.1700
Data Index: 312641 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8234. Min Range: -8.8234
Max Act: 8.3859. Min Act: -0.1700
Data Index: 2888890 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19