Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2837. Min Range: -5.2837
Max Act: 5.2837. Min Act: -0.1700
Data Index: 8528638 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2837. Min Range: -5.2837
Max Act: 5.1900. Min Act: -0.1700
Data Index: 413741 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.9087. Min Act: -0.1700
Data Index: 8349678 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.8775. Min Act: -0.1700
Data Index: 1651383 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.8462. Min Act: -0.1700
Data Index: 2362222 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.8150. Min Act: -0.1700
Data Index: 2986572 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.8150. Min Act: -0.1700
Data Index: 6266211 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.8462. Min Act: -0.1700
Data Index: 8580106 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.8150. Min Act: -0.1700
Data Index: 4681683 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.8150. Min Act: -0.1700
Data Index: 4035792 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.7837. Min Act: -0.1700
Data Index: 424886 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.7525. Min Act: -0.1700
Data Index: 3934714 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.6899. Min Act: -0.1700
Data Index: 6117429 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.6899. Min Act: -0.1700
Data Index: 22694 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.7212. Min Act: -0.1700
Data Index: 5134231 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.7212. Min Act: -0.1700
Data Index: 3759744 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.6899. Min Act: -0.1700
Data Index: 19822 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.7212. Min Act: -0.1700
Data Index: 4170421 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.6899. Min Act: -0.1700
Data Index: 3252797 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2837. Min Range: -5.2837
Max Act: 4.6587. Min Act: -0.1700
Data Index: 6749196 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19