Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1591 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.9665. Min Act: -0.1700
Data Index: 3402722 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.9348. Min Act: -0.1700
Data Index: 7800896 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.9348. Min Act: -0.1700
Data Index: 7819658 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.8555. Min Act: -0.1700
Data Index: 4706845 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.8396. Min Act: -0.1700
Data Index: 3787832 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.8237. Min Act: -0.1700
Data Index: 36158 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.8078. Min Act: -0.1700
Data Index: 7858259 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7600. Min Act: -0.1700
Data Index: 5587398 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7600. Min Act: -0.1700
Data Index: 555082 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7440. Min Act: -0.1700
Data Index: 5736084 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7600. Min Act: -0.1700
Data Index: 411945 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7440. Min Act: -0.1700
Data Index: 5694813 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7280. Min Act: -0.1700
Data Index: 6487982 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7280. Min Act: -0.1700
Data Index: 6432263 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.7280. Min Act: -0.1700
Data Index: 6177393 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.6961. Min Act: -0.1700
Data Index: 8784263 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.6961. Min Act: -0.1700
Data Index: 8309119 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.6961. Min Act: -0.1700
Data Index: 591785 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.6800. Min Act: -0.1700
Data Index: 4918845 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9665. Min Range: -2.9665
Max Act: 2.6640. Min Act: -0.1700
Data Index: 261296 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19