Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2747. Min Range: -4.2747
Max Act: 4.2747. Min Act: -0.1700
Data Index: 2286992 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2747. Min Range: -4.2747
Max Act: 4.1184. Min Act: -0.1700
Data Index: 943309 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2747. Min Range: -4.2747
Max Act: 4.0872. Min Act: -0.1700
Data Index: 8213636 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2747. Min Range: -4.2747
Max Act: 4.0872. Min Act: -0.1700
Data Index: 3076953 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2747. Min Range: -4.2747
Max Act: 4.0247. Min Act: -0.1700
Data Index: 1030325 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2747. Min Range: -4.2747
Max Act: 4.0559. Min Act: -0.1700
Data Index: 5273207 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9934. Min Act: -0.1700
Data Index: 2368756 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9621. Min Act: -0.1700
Data Index: 3867958 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9621. Min Act: -0.1700
Data Index: 7961366 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9621. Min Act: -0.1700
Data Index: 2538678 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9465. Min Act: -0.1700
Data Index: 7190264 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9465. Min Act: -0.1700
Data Index: 4354136 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9153. Min Act: -0.1700
Data Index: 1995025 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9309. Min Act: -0.1700
Data Index: 7402322 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9153. Min Act: -0.1700
Data Index: 2728013 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.8996. Min Act: -0.1700
Data Index: 6448301 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9153. Min Act: -0.1700
Data Index: 1634708 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9153. Min Act: -0.1700
Data Index: 5788603 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.8996. Min Act: -0.1700
Data Index: 1392437 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2747. Min Range: -4.2747
Max Act: 3.9153. Min Act: -0.1700
Data Index: 1331684 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19