Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4553 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.7452. Min Act: -0.1700
Data Index: 7742222 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.7132. Min Act: -0.1700
Data Index: 3983267 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.6491. Min Act: -0.1700
Data Index: 5705137 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.6331. Min Act: -0.1700
Data Index: 4357635 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.6009. Min Act: -0.1700
Data Index: 4808592 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.6009. Min Act: -0.1700
Data Index: 8596737 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5848. Min Act: -0.1700
Data Index: 6931391 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5526. Min Act: -0.1700
Data Index: 5531316 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5848. Min Act: -0.1700
Data Index: 5277440 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5526. Min Act: -0.1700
Data Index: 3747196 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5364. Min Act: -0.1700
Data Index: 6002010 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5364. Min Act: -0.1700
Data Index: 1749000 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5203. Min Act: -0.1700
Data Index: 8010487 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5041. Min Act: -0.1700
Data Index: 604520 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5041. Min Act: -0.1700
Data Index: 1615850 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5041. Min Act: -0.1700
Data Index: 4305749 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.4879. Min Act: -0.1700
Data Index: 759368 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5203. Min Act: -0.1700
Data Index: 7491869 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5041. Min Act: -0.1700
Data Index: 2407546 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7452. Min Range: -2.7452
Max Act: 2.5041. Min Act: -0.1700
Data Index: 379942 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19