Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1745 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3071. Min Range: -5.3071
Max Act: 5.3071. Min Act: -0.1700
Data Index: 6754598 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.9946. Min Act: -0.1700
Data Index: 7403885 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.7446. Min Act: -0.1700
Data Index: 634019 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.7133. Min Act: -0.1700
Data Index: 3130360 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.5571. Min Act: -0.1700
Data Index: 8706782 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.5571. Min Act: -0.1700
Data Index: 855555 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.5571. Min Act: -0.1700
Data Index: 5163504 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.5571. Min Act: -0.1700
Data Index: 3809274 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4946. Min Act: -0.1700
Data Index: 2588706 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4946. Min Act: -0.1700
Data Index: 1707212 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4946. Min Act: -0.1700
Data Index: 8435159 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4633. Min Act: -0.1700
Data Index: 307054 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4633. Min Act: -0.1700
Data Index: 375120 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4633. Min Act: -0.1700
Data Index: 6310054 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4320. Min Act: -0.1700
Data Index: 2922413 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4008. Min Act: -0.1700
Data Index: 2681390 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4008. Min Act: -0.1700
Data Index: 7756859 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4008. Min Act: -0.1700
Data Index: 5648270 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4008. Min Act: -0.1700
Data Index: 1377039 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3071. Min Range: -5.3071
Max Act: 4.4320. Min Act: -0.1700
Data Index: 4972688 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19