Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1925 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.9311. Min Act: -0.1700
Data Index: 6296842 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.7748. Min Act: -0.1700
Data Index: 2041035 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.7748. Min Act: -0.1700
Data Index: 2102085 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.7436. Min Act: -0.1700
Data Index: 347493 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.6498. Min Act: -0.1700
Data Index: 314581 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.6498. Min Act: -0.1700
Data Index: 3990075 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.6186. Min Act: -0.1700
Data Index: 1780638 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.5561. Min Act: -0.1700
Data Index: 3429236 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.5561. Min Act: -0.1700
Data Index: 6708731 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.5561. Min Act: -0.1700
Data Index: 1140204 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.5561. Min Act: -0.1700
Data Index: 3916642 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.4936. Min Act: -0.1700
Data Index: 2925549 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.5248. Min Act: -0.1700
Data Index: 1824243 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.5248. Min Act: -0.1700
Data Index: 2510917 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.5248. Min Act: -0.1700
Data Index: 7596538 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.4936. Min Act: -0.1700
Data Index: 1989545 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.4936. Min Act: -0.1700
Data Index: 8228195 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.4936. Min Act: -0.1700
Data Index: 5333282 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.4311. Min Act: -0.1700
Data Index: 7175265 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9311. Min Range: -4.9311
Max Act: 4.4936. Min Act: -0.1700
Data Index: 6655510 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19