Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1361 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0367. Min Range: -6.0367
Max Act: 6.0367. Min Act: -0.1700
Data Index: 6913126 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.9742. Min Act: -0.1700
Data Index: 542444 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.8180. Min Act: -0.1700
Data Index: 7430701 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.7867. Min Act: -0.1700
Data Index: 5065974 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.6930. Min Act: -0.1700
Data Index: 1084982 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.6930. Min Act: -0.1700
Data Index: 3194488 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.6930. Min Act: -0.1700
Data Index: 4975411 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.6305. Min Act: -0.1700
Data Index: 6761201 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.6305. Min Act: -0.1700
Data Index: 6151173 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.6305. Min Act: -0.1700
Data Index: 2062142 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5992. Min Act: -0.1700
Data Index: 5803148 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5992. Min Act: -0.1700
Data Index: 66579 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5367. Min Act: -0.1700
Data Index: 5120832 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5680. Min Act: -0.1700
Data Index: 3089723 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5367. Min Act: -0.1700
Data Index: 2048968 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5367. Min Act: -0.1700
Data Index: 2416655 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5055. Min Act: -0.1700
Data Index: 5038988 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5367. Min Act: -0.1700
Data Index: 7030595 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5367. Min Act: -0.1700
Data Index: 5391493 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0367. Min Range: -6.0367
Max Act: 5.5055. Min Act: -0.1700
Data Index: 5195513 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19