Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2347 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.3146. Min Act: -0.1700
Data Index: 6068416 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.2833. Min Act: -0.1700
Data Index: 8576845 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.2521. Min Act: -0.1700
Data Index: 4940060 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0958. Min Act: -0.1700
Data Index: 7683417 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8025800 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0958. Min Act: -0.1700
Data Index: 3137137 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0646. Min Act: -0.1700
Data Index: 6493488 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0646. Min Act: -0.1700
Data Index: 587107 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3514864 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0646. Min Act: -0.1700
Data Index: 5376645 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0333. Min Act: -0.1700
Data Index: 5208660 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3146. Min Range: -5.3146
Max Act: 5.0021. Min Act: -0.1700
Data Index: 1229702 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9708. Min Act: -0.1700
Data Index: 2423008 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9708. Min Act: -0.1700
Data Index: 5847321 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9708. Min Act: -0.1700
Data Index: 3578034 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9708. Min Act: -0.1700
Data Index: 7639437 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9708. Min Act: -0.1700
Data Index: 1965381 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9396. Min Act: -0.1700
Data Index: 8722424 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9396. Min Act: -0.1700
Data Index: 4686947 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3146. Min Range: -5.3146
Max Act: 4.9083. Min Act: -0.1700
Data Index: 7639425 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19