Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.5222. Min Act: -0.1700
Data Index: 2934002 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.4285. Min Act: -0.1700
Data Index: 3777825 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.3972. Min Act: -0.1700
Data Index: 3674380 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.3660. Min Act: -0.1700
Data Index: 1754297 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.3347. Min Act: -0.1700
Data Index: 2732885 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.3035. Min Act: -0.1700
Data Index: 7189904 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.3035. Min Act: -0.1700
Data Index: 7051965 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2410. Min Act: -0.1700
Data Index: 3649805 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2410. Min Act: -0.1700
Data Index: 3889345 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2722. Min Act: -0.1700
Data Index: 314647 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2097. Min Act: -0.1700
Data Index: 7584431 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2410. Min Act: -0.1700
Data Index: 5633854 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2410. Min Act: -0.1700
Data Index: 4260578 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2722. Min Act: -0.1700
Data Index: 1193922 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.1785. Min Act: -0.1700
Data Index: 5126404 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.1785. Min Act: -0.1700
Data Index: 5269133 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2097. Min Act: -0.1700
Data Index: 4051782 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2410. Min Act: -0.1700
Data Index: 698212 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2097. Min Act: -0.1700
Data Index: 8733729 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5222. Min Range: -5.5222
Max Act: 5.2097. Min Act: -0.1700
Data Index: 248274 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19