Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1316. Min Range: -5.1316
Max Act: 5.1316. Min Act: -0.1700
Data Index: 1744417 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1316. Min Range: -5.1316
Max Act: 5.1003. Min Act: -0.1700
Data Index: 4901568 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1316. Min Range: -5.1316
Max Act: 5.0066. Min Act: -0.1700
Data Index: 4367261 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1316. Min Range: -5.1316
Max Act: 5.0066. Min Act: -0.1700
Data Index: 2542494 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1316. Min Range: -5.1316
Max Act: 5.0066. Min Act: -0.1700
Data Index: 7268849 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9753. Min Act: -0.1700
Data Index: 2250899 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9441. Min Act: -0.1700
Data Index: 541171 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1316. Min Range: -5.1316
Max Act: 5.0066. Min Act: -0.1700
Data Index: 8656568 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9128. Min Act: -0.1700
Data Index: 8301968 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9441. Min Act: -0.1700
Data Index: 8635968 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9128. Min Act: -0.1700
Data Index: 5249050 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9441. Min Act: -0.1700
Data Index: 2970280 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9441. Min Act: -0.1700
Data Index: 1680662 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9441. Min Act: -0.1700
Data Index: 7242026 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9128. Min Act: -0.1700
Data Index: 5259806 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.9128. Min Act: -0.1700
Data Index: 3736992 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.8816. Min Act: -0.1700
Data Index: 6829630 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.8816. Min Act: -0.1700
Data Index: 4865957 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.8816. Min Act: -0.1700
Data Index: 4092878 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1316. Min Range: -5.1316
Max Act: 4.8816. Min Act: -0.1700
Data Index: 2578268 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19