Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4689 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0483. Min Range: -5.0483
Max Act: 5.0483. Min Act: -0.1700
Data Index: 5124277 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.8920. Min Act: -0.1700
Data Index: 4654161 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.8920. Min Act: -0.1700
Data Index: 3701860 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.8608. Min Act: -0.1700
Data Index: 2758012 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.8295. Min Act: -0.1700
Data Index: 5929233 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.7358. Min Act: -0.1700
Data Index: 7280658 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.7358. Min Act: -0.1700
Data Index: 994794 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.7358. Min Act: -0.1700
Data Index: 493078 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.7045. Min Act: -0.1700
Data Index: 6836350 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.7045. Min Act: -0.1700
Data Index: 4433319 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6733. Min Act: -0.1700
Data Index: 1663664 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6420. Min Act: -0.1700
Data Index: 3189171 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6108. Min Act: -0.1700
Data Index: 7539236 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6108. Min Act: -0.1700
Data Index: 3554159 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6733. Min Act: -0.1700
Data Index: 2622496 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6108. Min Act: -0.1700
Data Index: 5085723 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6108. Min Act: -0.1700
Data Index: 8080519 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6108. Min Act: -0.1700
Data Index: 638451 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.6108. Min Act: -0.1700
Data Index: 7261871 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0483. Min Range: -5.0483
Max Act: 4.5795. Min Act: -0.1700
Data Index: 6546642 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19