Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.6247. Min Act: -0.1700
Data Index: 6542291 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.2809. Min Act: -0.1700
Data Index: 3229344 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.1559. Min Act: -0.1700
Data Index: 3952931 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.0934. Min Act: -0.1700
Data Index: 5376783 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.1247. Min Act: -0.1700
Data Index: 6834577 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.0622. Min Act: -0.1700
Data Index: 1659929 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.0622. Min Act: -0.1700
Data Index: 551514 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.0309. Min Act: -0.1700
Data Index: 8655951 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6247. Min Range: -6.6247
Max Act: 6.0309. Min Act: -0.1700
Data Index: 4683980 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.9372. Min Act: -0.1700
Data Index: 7155009 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.9997. Min Act: -0.1700
Data Index: 7019224 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.9059. Min Act: -0.1700
Data Index: 6615035 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.8747. Min Act: -0.1700
Data Index: 1689569 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.9059. Min Act: -0.1700
Data Index: 5154392 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.8747. Min Act: -0.1700
Data Index: 1037249 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.8747. Min Act: -0.1700
Data Index: 6654614 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.9059. Min Act: -0.1700
Data Index: 5403282 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.8747. Min Act: -0.1700
Data Index: 8452445 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.8434. Min Act: -0.1700
Data Index: 3293092 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6247. Min Range: -6.6247
Max Act: 5.8122. Min Act: -0.1700
Data Index: 4013027 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19