Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1877 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1224. Min Range: -3.1224
Max Act: 3.1224. Min Act: -0.1700
Data Index: 4498756 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1224. Min Range: -3.1224
Max Act: 3.0908. Min Act: -0.1700
Data Index: 4393621 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1224. Min Range: -3.1224
Max Act: 3.0119. Min Act: -0.1700
Data Index: 5683079 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.9961. Min Act: -0.1700
Data Index: 5434127 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.9011. Min Act: -0.1700
Data Index: 7221253 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8694. Min Act: -0.1700
Data Index: 8626597 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8535. Min Act: -0.1700
Data Index: 412738 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8535. Min Act: -0.1700
Data Index: 4092586 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8376. Min Act: -0.1700
Data Index: 1874860 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8217. Min Act: -0.1700
Data Index: 3211381 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.7899. Min Act: -0.1700
Data Index: 311107 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8058. Min Act: -0.1700
Data Index: 3152271 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8058. Min Act: -0.1700
Data Index: 117287 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8058. Min Act: -0.1700
Data Index: 7271489 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.8058. Min Act: -0.1700
Data Index: 5080224 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.7899. Min Act: -0.1700
Data Index: 2277798 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.7899. Min Act: -0.1700
Data Index: 2260784 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.7740. Min Act: -0.1700
Data Index: 3076929 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.7899. Min Act: -0.1700
Data Index: 5295631 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1224. Min Range: -3.1224
Max Act: 2.7580. Min Act: -0.1700
Data Index: 655005 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19