Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1540. Min Range: -7.1540
Max Act: 7.1540. Min Act: -0.1700
Data Index: 6755851 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.9040. Min Act: -0.1700
Data Index: 4602545 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.8102. Min Act: -0.1700
Data Index: 4514507 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.7790. Min Act: -0.1700
Data Index: 2931342 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.7477. Min Act: -0.1700
Data Index: 168388 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.7165. Min Act: -0.1700
Data Index: 1264410 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.7165. Min Act: -0.1700
Data Index: 1758703 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.7165. Min Act: -0.1700
Data Index: 3291504 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6540. Min Act: -0.1700
Data Index: 6488064 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6540. Min Act: -0.1700
Data Index: 8523154 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6227. Min Act: -0.1700
Data Index: 276400 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6227. Min Act: -0.1700
Data Index: 1522997 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6540. Min Act: -0.1700
Data Index: 2003079 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6227. Min Act: -0.1700
Data Index: 7260705 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6227. Min Act: -0.1700
Data Index: 6825814 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6227. Min Act: -0.1700
Data Index: 3851078 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6227. Min Act: -0.1700
Data Index: 896379 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.6227. Min Act: -0.1700
Data Index: 2039418 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.5915. Min Act: -0.1700
Data Index: 4538118 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1540. Min Range: -7.1540
Max Act: 6.5915. Min Act: -0.1700
Data Index: 7066540 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19