Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1440 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.2222. Min Act: -0.1700
Data Index: 6852595 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.1597. Min Act: -0.1700
Data Index: 8659562 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0972. Min Act: -0.1700
Data Index: 1055349 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0660. Min Act: -0.1700
Data Index: 5401977 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0347. Min Act: -0.1700
Data Index: 3472140 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0660. Min Act: -0.1700
Data Index: 7784302 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0035. Min Act: -0.1700
Data Index: 2116332 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0035. Min Act: -0.1700
Data Index: 4499656 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0035. Min Act: -0.1700
Data Index: 4048112 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0035. Min Act: -0.1700
Data Index: 240872 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0035. Min Act: -0.1700
Data Index: 38948 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2222. Min Range: -5.2222
Max Act: 5.0035. Min Act: -0.1700
Data Index: 6280910 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.9722. Min Act: -0.1700
Data Index: 121876 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.9410. Min Act: -0.1700
Data Index: 5668189 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.9410. Min Act: -0.1700
Data Index: 8205584 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.9410. Min Act: -0.1700
Data Index: 7787991 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.9410. Min Act: -0.1700
Data Index: 3917179 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.9097. Min Act: -0.1700
Data Index: 7191681 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.8785. Min Act: -0.1700
Data Index: 844926 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2222. Min Range: -5.2222
Max Act: 4.9097. Min Act: -0.1700
Data Index: 4351689 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19