Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4762 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.7419. Min Act: -0.1700
Data Index: 1179863 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.5232. Min Act: -0.1700
Data Index: 7308013 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.4919. Min Act: -0.1700
Data Index: 5020430 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.4607. Min Act: -0.1700
Data Index: 604926 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.4607. Min Act: -0.1700
Data Index: 5756693 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3982. Min Act: -0.1700
Data Index: 6110407 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.4294. Min Act: -0.1700
Data Index: 1720745 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.4294. Min Act: -0.1700
Data Index: 1792139 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.4294. Min Act: -0.1700
Data Index: 1235317 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3982. Min Act: -0.1700
Data Index: 155033 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3982. Min Act: -0.1700
Data Index: 10580 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3982. Min Act: -0.1700
Data Index: 4930584 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3982. Min Act: -0.1700
Data Index: 518618 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3669. Min Act: -0.1700
Data Index: 1321886 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3669. Min Act: -0.1700
Data Index: 7934073 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3669. Min Act: -0.1700
Data Index: 7675723 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3669. Min Act: -0.1700
Data Index: 2661385 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3357. Min Act: -0.1700
Data Index: 7759627 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3357. Min Act: -0.1700
Data Index: 7604846 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7419. Min Range: -5.7419
Max Act: 5.3044. Min Act: -0.1700
Data Index: 7512616 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19