Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.9735. Min Act: -0.1700
Data Index: 8276622 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.9423. Min Act: -0.1700
Data Index: 5072657 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.9423. Min Act: -0.1700
Data Index: 1568391 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.9110. Min Act: -0.1700
Data Index: 6746840 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.8798. Min Act: -0.1700
Data Index: 7814426 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.8485. Min Act: -0.1700
Data Index: 1215946 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.8173. Min Act: -0.1700
Data Index: 2849219 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.7548. Min Act: -0.1700
Data Index: 2592007 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.7235. Min Act: -0.1700
Data Index: 2605708 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.6610. Min Act: -0.1700
Data Index: 7678801 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5985. Min Act: -0.1700
Data Index: 1531528 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5985. Min Act: -0.1700
Data Index: 4436667 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5985. Min Act: -0.1700
Data Index: 2259301 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5985. Min Act: -0.1700
Data Index: 6276959 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5985. Min Act: -0.1700
Data Index: 3254422 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5360. Min Act: -0.1700
Data Index: 6310601 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5048. Min Act: -0.1700
Data Index: 2579711 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.5048. Min Act: -0.1700
Data Index: 5651421 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.4735. Min Act: -0.1700
Data Index: 5722635 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9735. Min Range: -5.9735
Max Act: 5.4735. Min Act: -0.1700
Data Index: 4424681 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19