Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4588. Min Range: -8.4588
Max Act: 8.4588. Min Act: -0.1700
Data Index: 7295974 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4588. Min Range: -8.4588
Max Act: 8.4588. Min Act: -0.1700
Data Index: 716382 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4588. Min Range: -8.4588
Max Act: 8.0838. Min Act: -0.1700
Data Index: 495760 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4588. Min Range: -8.4588
Max Act: 8.0525. Min Act: -0.1700
Data Index: 4675875 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4588. Min Range: -8.4588
Max Act: 8.0213. Min Act: -0.1700
Data Index: 3126437 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4588. Min Range: -8.4588
Max Act: 8.0213. Min Act: -0.1700
Data Index: 3004197 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.9900. Min Act: -0.1700
Data Index: 3911826 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.9275. Min Act: -0.1700
Data Index: 5002798 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.8650. Min Act: -0.1700
Data Index: 617112 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.8650. Min Act: -0.1700
Data Index: 7628332 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.8338. Min Act: -0.1700
Data Index: 2477352 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.8025. Min Act: -0.1700
Data Index: 3059697 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.8650. Min Act: -0.1700
Data Index: 4935705 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.8025. Min Act: -0.1700
Data Index: 6426662 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.7713. Min Act: -0.1700
Data Index: 501983 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.7713. Min Act: -0.1700
Data Index: 6363452 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.7400. Min Act: -0.1700
Data Index: 8702965 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.6463. Min Act: -0.1700
Data Index: 3013959 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.6150. Min Act: -0.1700
Data Index: 3186091 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4588. Min Range: -8.4588
Max Act: 7.6150. Min Act: -0.1700
Data Index: 6371526 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19