Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5358 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.7464. Min Act: -0.1700
Data Index: 3392516 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.7291. Min Act: -0.1699
Data Index: 8329082 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.7118. Min Act: -0.1700
Data Index: 6214208 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6771. Min Act: -0.1700
Data Index: 2382132 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6771. Min Act: -0.1700
Data Index: 8221358 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6597. Min Act: -0.1700
Data Index: 8107847 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6597. Min Act: -0.1700
Data Index: 1729666 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6423. Min Act: -0.1700
Data Index: 8107846 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6597. Min Act: -0.1700
Data Index: 4327884 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6423. Min Act: -0.1700
Data Index: 3319370 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5900. Min Act: -0.1690
Data Index: 50749 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.6074. Min Act: -0.1697
Data Index: 4971908 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5900. Min Act: -0.1700
Data Index: 2243030 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5900. Min Act: -0.1692
Data Index: 4973876 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5900. Min Act: -0.1686
Data Index: 4463035 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5725. Min Act: -0.1700
Data Index: 1772808 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5725. Min Act: -0.1678
Data Index: 4146866 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5900. Min Act: -0.1700
Data Index: 2243028 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5550. Min Act: -0.1700
Data Index: 2243025 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7464. Min Range: -1.7464
Max Act: 1.5550. Min Act: -0.1700
Data Index: 7600395 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19