Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 295 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0633. Min Range: -5.0633
Max Act: 5.0633. Min Act: -0.1700
Data Index: 5983489 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.9383. Min Act: -0.1700
Data Index: 4936586 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.9383. Min Act: -0.1700
Data Index: 4482129 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.9070. Min Act: -0.1700
Data Index: 173274 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.8758. Min Act: -0.1700
Data Index: 4236444 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.8758. Min Act: -0.1700
Data Index: 7455882 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2660581 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2105547 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.8133. Min Act: -0.1700
Data Index: 53793 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.8133. Min Act: -0.1700
Data Index: 3002311 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7820. Min Act: -0.1700
Data Index: 1812449 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7820. Min Act: -0.1700
Data Index: 6649248 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7820. Min Act: -0.1700
Data Index: 1631833 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7820. Min Act: -0.1700
Data Index: 5068210 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7508. Min Act: -0.1700
Data Index: 1842821 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7820. Min Act: -0.1700
Data Index: 8592958 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7820. Min Act: -0.1700
Data Index: 8692227 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7508. Min Act: -0.1700
Data Index: 1891591 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7508. Min Act: -0.1700
Data Index: 2120700 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0633. Min Range: -5.0633
Max Act: 4.7820. Min Act: -0.1700
Data Index: 4438128 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19