Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.2697. Min Act: -0.1700
Data Index: 1450645 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.2854. Min Act: -0.1700
Data Index: 8515150 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.2540. Min Act: -0.1700
Data Index: 6407963 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.2383. Min Act: -0.1700
Data Index: 7136583 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.2069. Min Act: -0.1700
Data Index: 4301792 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.1911. Min Act: -0.1700
Data Index: 1076855 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.1754. Min Act: -0.1700
Data Index: 1676067 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.1597. Min Act: -0.1700
Data Index: 3432120 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.1597. Min Act: -0.1700
Data Index: 244530 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.1439. Min Act: -0.1700
Data Index: 4412588 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.1282. Min Act: -0.1700
Data Index: 3425352 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.1439. Min Act: -0.1700
Data Index: 7255101 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0967. Min Act: -0.1700
Data Index: 4695620 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0809. Min Act: -0.1700
Data Index: 6569649 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0651. Min Act: -0.1700
Data Index: 7273224 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0809. Min Act: -0.1700
Data Index: 5870359 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0651. Min Act: -0.1700
Data Index: 2234357 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0967. Min Act: -0.1700
Data Index: 4412587 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0651. Min Act: -0.1700
Data Index: 4533849 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2854. Min Range: -3.2854
Max Act: 3.0494. Min Act: -0.1700
Data Index: 8056231 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19