Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.8788. Min Act: -0.1700
Data Index: 8604558 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.6288. Min Act: -0.1700
Data Index: 3845553 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.5976. Min Act: -0.1700
Data Index: 1445402 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.5663. Min Act: -0.1700
Data Index: 7684195 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.5350. Min Act: -0.1700
Data Index: 1383197 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.5350. Min Act: -0.1700
Data Index: 8357687 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.5038. Min Act: -0.1700
Data Index: 1122881 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4725. Min Act: -0.1700
Data Index: 3995135 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4725. Min Act: -0.1700
Data Index: 6777528 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4725. Min Act: -0.1700
Data Index: 7272775 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4725. Min Act: -0.1700
Data Index: 7490087 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4725. Min Act: -0.1700
Data Index: 7973317 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4413. Min Act: -0.1700
Data Index: 3443313 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4413. Min Act: -0.1700
Data Index: 2552989 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4413. Min Act: -0.1700
Data Index: 4142457 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4725. Min Act: -0.1700
Data Index: 750015 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4100. Min Act: -0.1700
Data Index: 4335874 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.4413. Min Act: -0.1700
Data Index: 4389959 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.3788. Min Act: -0.1700
Data Index: 3448685 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8788. Min Range: -4.8788
Max Act: 4.3788. Min Act: -0.1700
Data Index: 2493320 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19