Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1570 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3946. Min Range: -5.3946
Max Act: 5.3946. Min Act: -0.1700
Data Index: 6436357 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3946. Min Range: -5.3946
Max Act: 5.1446. Min Act: -0.1700
Data Index: 65243 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.8946. Min Act: -0.1700
Data Index: 8789949 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.7696. Min Act: -0.1700
Data Index: 6874972 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.7696. Min Act: -0.1700
Data Index: 7124991 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.7383. Min Act: -0.1700
Data Index: 8387467 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.7383. Min Act: -0.1700
Data Index: 4792919 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.6758. Min Act: -0.1700
Data Index: 1463667 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.6446. Min Act: -0.1700
Data Index: 1072862 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.6446. Min Act: -0.1700
Data Index: 5710630 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.6133. Min Act: -0.1700
Data Index: 4629363 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.6133. Min Act: -0.1700
Data Index: 966191 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.6133. Min Act: -0.1700
Data Index: 4030967 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.5821. Min Act: -0.1700
Data Index: 8822603 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.5821. Min Act: -0.1700
Data Index: 6716917 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.5508. Min Act: -0.1700
Data Index: 6136396 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.5508. Min Act: -0.1700
Data Index: 2208478 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.5508. Min Act: -0.1700
Data Index: 1144781 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.5508. Min Act: -0.1700
Data Index: 5366042 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3946. Min Range: -5.3946
Max Act: 4.5196. Min Act: -0.1700
Data Index: 3059730 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19