Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.4189. Min Act: -0.1700
Data Index: 4650868 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.4189. Min Act: -0.1700
Data Index: 7115837 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.4189. Min Act: -0.1700
Data Index: 4371678 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.3564. Min Act: -0.1700
Data Index: 3663830 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.3564. Min Act: -0.1700
Data Index: 7488550 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.3564. Min Act: -0.1700
Data Index: 8598219 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.3251. Min Act: -0.1700
Data Index: 8816423 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2939. Min Act: -0.1700
Data Index: 5810456 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2939. Min Act: -0.1700
Data Index: 3591041 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2626. Min Act: -0.1700
Data Index: 4837308 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2314. Min Act: -0.1700
Data Index: 976066 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2314. Min Act: -0.1700
Data Index: 27544 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2001. Min Act: -0.1700
Data Index: 3314049 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2314. Min Act: -0.1700
Data Index: 7228825 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2001. Min Act: -0.1700
Data Index: 4520565 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.2001. Min Act: -0.1700
Data Index: 2722362 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.1689. Min Act: -0.1700
Data Index: 4405466 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.1689. Min Act: -0.1700
Data Index: 502722 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.1689. Min Act: -0.1700
Data Index: 6701938 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4189. Min Range: -4.4189
Max Act: 4.1376. Min Act: -0.1700
Data Index: 7506147 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19