Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0990. Min Range: -7.0990
Max Act: 7.0990. Min Act: -0.1700
Data Index: 5647120 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.6303. Min Act: -0.1700
Data Index: 1290589 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.5990. Min Act: -0.1700
Data Index: 1068561 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.5678. Min Act: -0.1700
Data Index: 8156367 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.5365. Min Act: -0.1700
Data Index: 1964924 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.5365. Min Act: -0.1700
Data Index: 1346828 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.5053. Min Act: -0.1700
Data Index: 3403678 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.5053. Min Act: -0.1700
Data Index: 2946581 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.4428. Min Act: -0.1700
Data Index: 20442 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.4428. Min Act: -0.1700
Data Index: 1964922 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.4115. Min Act: -0.1700
Data Index: 7301105 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.3803. Min Act: -0.1700
Data Index: 7102864 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.3803. Min Act: -0.1700
Data Index: 3998999 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.3490. Min Act: -0.1700
Data Index: 6732514 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.3178. Min Act: -0.1700
Data Index: 7102866 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.2865. Min Act: -0.1700
Data Index: 8000666 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.2553. Min Act: -0.1700
Data Index: 1964929 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.2553. Min Act: -0.1700
Data Index: 4982618 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.2240. Min Act: -0.1700
Data Index: 5295588 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0990. Min Range: -7.0990
Max Act: 6.2240. Min Act: -0.1700
Data Index: 246287 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19