Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.9395. Min Act: -0.1700
Data Index: 8749873 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8602. Min Act: -0.1700
Data Index: 7392273 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8760. Min Act: -0.1700
Data Index: 5531260 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8602. Min Act: -0.1700
Data Index: 8108783 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8760. Min Act: -0.1700
Data Index: 4016319 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8760. Min Act: -0.1700
Data Index: 849038 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.7966. Min Act: -0.1700
Data Index: 8428672 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8443. Min Act: -0.1700
Data Index: 6117078 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8443. Min Act: -0.1700
Data Index: 1778343 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8284. Min Act: -0.1700
Data Index: 5687226 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8284. Min Act: -0.1700
Data Index: 7794203 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8284. Min Act: -0.1700
Data Index: 8368921 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8125. Min Act: -0.1700
Data Index: 8696011 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.7966. Min Act: -0.1700
Data Index: 2511422 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8443. Min Act: -0.1700
Data Index: 4616317 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8284. Min Act: -0.1700
Data Index: 8641740 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8125. Min Act: -0.1700
Data Index: 5269445 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8125. Min Act: -0.1700
Data Index: 6520257 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8284. Min Act: -0.1700
Data Index: 8311449 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9395. Min Range: -2.9395
Max Act: 2.8125. Min Act: -0.1700
Data Index: 6687750 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19