Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5359. Min Range: -7.5359
Max Act: 7.5359. Min Act: -0.1700
Data Index: 1035361 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5359. Min Range: -7.5359
Max Act: 7.4422. Min Act: -0.1700
Data Index: 3160747 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5359. Min Range: -7.5359
Max Act: 7.1922. Min Act: -0.1700
Data Index: 6620727 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5359. Min Range: -7.5359
Max Act: 7.0672. Min Act: -0.1700
Data Index: 1362092 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5359. Min Range: -7.5359
Max Act: 7.0672. Min Act: -0.1700
Data Index: 3160748 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.9109. Min Act: -0.1700
Data Index: 3480410 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.8797. Min Act: -0.1700
Data Index: 279064 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.8797. Min Act: -0.1700
Data Index: 233122 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.8172. Min Act: -0.1700
Data Index: 1338346 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.8172. Min Act: -0.1700
Data Index: 1711232 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.7859. Min Act: -0.1700
Data Index: 2641731 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.7859. Min Act: -0.1700
Data Index: 2034960 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.7547. Min Act: -0.1700
Data Index: 7554617 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.7234. Min Act: -0.1700
Data Index: 8417009 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.7547. Min Act: -0.1700
Data Index: 1230963 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.6922. Min Act: -0.1700
Data Index: 4373235 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.6922. Min Act: -0.1700
Data Index: 1168184 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.6922. Min Act: -0.1700
Data Index: 985822 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.6922. Min Act: -0.1700
Data Index: 6172905 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5359. Min Range: -7.5359
Max Act: 6.6922. Min Act: -0.1700
Data Index: 120352 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19