Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.4406. Min Act: -0.1700
Data Index: 7614159 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.1906. Min Act: -0.1700
Data Index: 3344885 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.1906. Min Act: -0.1700
Data Index: 7301252 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.1593. Min Act: -0.1700
Data Index: 7210088 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.1281. Min Act: -0.1700
Data Index: 8682792 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.1281. Min Act: -0.1700
Data Index: 8682392 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0968. Min Act: -0.1700
Data Index: 6435438 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0656. Min Act: -0.1700
Data Index: 1311573 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0656. Min Act: -0.1700
Data Index: 5999640 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0343. Min Act: -0.1700
Data Index: 165218 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0343. Min Act: -0.1700
Data Index: 2932418 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0343. Min Act: -0.1700
Data Index: 5000343 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0343. Min Act: -0.1700
Data Index: 3085958 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0656. Min Act: -0.1700
Data Index: 4319974 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0343. Min Act: -0.1700
Data Index: 8776441 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4406. Min Range: -5.4406
Max Act: 4.9718. Min Act: -0.1700
Data Index: 6319562 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0031. Min Act: -0.1700
Data Index: 6517501 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4406. Min Range: -5.4406
Max Act: 4.9718. Min Act: -0.1700
Data Index: 6254561 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4406. Min Range: -5.4406
Max Act: 4.9718. Min Act: -0.1700
Data Index: 6180155 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4406. Min Range: -5.4406
Max Act: 5.0031. Min Act: -0.1700
Data Index: 236803 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19