Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2382 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4271. Min Range: -9.4271
Max Act: 9.4271. Min Act: -0.1700
Data Index: 2075798 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4271. Min Range: -9.4271
Max Act: 9.2396. Min Act: -0.1700
Data Index: 4485222 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.9896. Min Act: -0.1700
Data Index: 4369592 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.9271. Min Act: -0.1700
Data Index: 715361 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8646. Min Act: -0.1700
Data Index: 2045492 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8021. Min Act: -0.1700
Data Index: 5621085 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8646. Min Act: -0.1700
Data Index: 5558848 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8646. Min Act: -0.1700
Data Index: 613880 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8021. Min Act: -0.1700
Data Index: 3150026 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8021. Min Act: -0.1700
Data Index: 7780400 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8021. Min Act: -0.1700
Data Index: 4938505 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8021. Min Act: -0.1700
Data Index: 1332764 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.8021. Min Act: -0.1700
Data Index: 2092676 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.6771. Min Act: -0.1700
Data Index: 8710519 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.6771. Min Act: -0.1700
Data Index: 5992864 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.6771. Min Act: -0.1700
Data Index: 8425467 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.6771. Min Act: -0.1700
Data Index: 8388458 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.6146. Min Act: -0.1700
Data Index: 425050 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.6146. Min Act: -0.1700
Data Index: 7048264 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4271. Min Range: -9.4271
Max Act: 8.6146. Min Act: -0.1700
Data Index: 7083603 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19