Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 283 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.1021. Min Act: -0.1700
Data Index: 3678835 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.1336. Min Act: -0.1700
Data Index: 5942500 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.1021. Min Act: -0.1700
Data Index: 4156815 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.0863. Min Act: -0.1700
Data Index: 5847046 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.0232. Min Act: -0.1700
Data Index: 5430763 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.0232. Min Act: -0.1700
Data Index: 2061373 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.0390. Min Act: -0.1700
Data Index: 7261387 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9916. Min Act: -0.1700
Data Index: 5195583 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.0390. Min Act: -0.1700
Data Index: 4705705 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.0232. Min Act: -0.1700
Data Index: 6291910 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1336. Min Range: -3.1336
Max Act: 3.0074. Min Act: -0.1700
Data Index: 7451450 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9758. Min Act: -0.1700
Data Index: 4740604 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9916. Min Act: -0.1700
Data Index: 8785040 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9600. Min Act: -0.1700
Data Index: 5579890 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9441. Min Act: -0.1700
Data Index: 8142661 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9441. Min Act: -0.1700
Data Index: 6282452 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9441. Min Act: -0.1700
Data Index: 6051498 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9283. Min Act: -0.1700
Data Index: 8394248 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9758. Min Act: -0.1700
Data Index: 6450428 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1336. Min Range: -3.1336
Max Act: 2.9125. Min Act: -0.1700
Data Index: 4892123 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19