Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0511. Min Range: -1.0511
Max Act: 1.0511. Min Act: -0.1700
Data Index: 3914490 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0511. Min Range: -1.0511
Max Act: 1.0249. Min Act: -0.1700
Data Index: 339936 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9902. Min Act: -0.1700
Data Index: 4813128 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9902. Min Act: -0.1700
Data Index: 2433306 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9815. Min Act: -0.1700
Data Index: 8391182 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9729. Min Act: -0.1700
Data Index: 3811519 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9815. Min Act: -0.1700
Data Index: 3551104 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9815. Min Act: -0.1700
Data Index: 8175668 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9642. Min Act: -0.1700
Data Index: 2328508 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9729. Min Act: -0.1700
Data Index: 2289918 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9729. Min Act: -0.1700
Data Index: 7233311 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9384. Min Act: -0.1700
Data Index: 5429543 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9384. Min Act: -0.1700
Data Index: 5573848 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9384. Min Act: -0.1700
Data Index: 5961290 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9470. Min Act: -0.1700
Data Index: 689581 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9298. Min Act: -0.1700
Data Index: 8471565 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9384. Min Act: -0.1700
Data Index: 6575645 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9384. Min Act: -0.1700
Data Index: 8434488 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9212. Min Act: -0.1700
Data Index: 4123082 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0511. Min Range: -1.0511
Max Act: 0.9212. Min Act: -0.1700
Data Index: 6900591 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19