Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1696. Min Range: -6.1696
Max Act: 6.1696. Min Act: -0.1700
Data Index: 2280355 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.8883. Min Act: -0.1700
Data Index: 1851572 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.8883. Min Act: -0.1700
Data Index: 1572387 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.8571. Min Act: -0.1700
Data Index: 5539852 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.8258. Min Act: -0.1700
Data Index: 3984080 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.8571. Min Act: -0.1700
Data Index: 3598933 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.8258. Min Act: -0.1700
Data Index: 3749649 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.7946. Min Act: -0.1700
Data Index: 3257432 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.7321. Min Act: -0.1700
Data Index: 3054826 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.7321. Min Act: -0.1700
Data Index: 6911253 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.6383. Min Act: -0.1700
Data Index: 6314292 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.6383. Min Act: -0.1700
Data Index: 7413449 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.6383. Min Act: -0.1700
Data Index: 8672000 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.6383. Min Act: -0.1700
Data Index: 4917140 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.6071. Min Act: -0.1700
Data Index: 4828917 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.6071. Min Act: -0.1700
Data Index: 4766785 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.5758. Min Act: -0.1700
Data Index: 5186209 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.6071. Min Act: -0.1700
Data Index: 1441049 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.5758. Min Act: -0.1700
Data Index: 3524391 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1696. Min Range: -6.1696
Max Act: 5.5446. Min Act: -0.1700
Data Index: 340122 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19