Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2288 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.2692. Min Act: -0.1700
Data Index: 5579169 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9254. Min Act: -0.1700
Data Index: 4231691 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9254. Min Act: -0.1700
Data Index: 4569611 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8629. Min Act: -0.1700
Data Index: 3095480 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8317. Min Act: -0.1700
Data Index: 1513546 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7692. Min Act: -0.1700
Data Index: 1276251 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.5817. Min Act: -0.1700
Data Index: 7604930 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.6129. Min Act: -0.1700
Data Index: 6394223 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4879. Min Act: -0.1700
Data Index: 1690553 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4879. Min Act: -0.1700
Data Index: 1247141 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.5192. Min Act: -0.1700
Data Index: 7113050 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1022500 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4879. Min Act: -0.1700
Data Index: 391537 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 3487580 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 3796303 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.5192. Min Act: -0.1700
Data Index: 7952182 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.3942. Min Act: -0.1700
Data Index: 6963581 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4879. Min Act: -0.1700
Data Index: 8537305 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 4612056 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.4567. Min Act: -0.1700
Data Index: 1607686 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19