Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2348. Min Range: -6.2348
Max Act: 6.2348. Min Act: -0.1700
Data Index: 6047383 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2348. Min Range: -6.2348
Max Act: 6.1411. Min Act: -0.1700
Data Index: 5715449 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2348. Min Range: -6.2348
Max Act: 6.0473. Min Act: -0.1700
Data Index: 2837415 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2348. Min Range: -6.2348
Max Act: 6.0473. Min Act: -0.1700
Data Index: 8698002 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.9223. Min Act: -0.1700
Data Index: 8312734 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.9223. Min Act: -0.1700
Data Index: 7948511 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.8598. Min Act: -0.1700
Data Index: 5174460 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.8598. Min Act: -0.1700
Data Index: 3983093 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.8598. Min Act: -0.1700
Data Index: 5316326 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.8286. Min Act: -0.1700
Data Index: 8207712 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7973. Min Act: -0.1700
Data Index: 5975988 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.8286. Min Act: -0.1700
Data Index: 3665575 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.8286. Min Act: -0.1700
Data Index: 6721783 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7973. Min Act: -0.1700
Data Index: 8457155 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7973. Min Act: -0.1700
Data Index: 5356827 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7973. Min Act: -0.1700
Data Index: 4168470 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7973. Min Act: -0.1700
Data Index: 2033911 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4935323 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7661. Min Act: -0.1700
Data Index: 1133877 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2348. Min Range: -6.2348
Max Act: 5.7661. Min Act: -0.1700
Data Index: 5397745 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19