Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5380 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.9659. Min Act: -0.1700
Data Index: 6418308 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.9346. Min Act: -0.1700
Data Index: 7644944 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.9034. Min Act: -0.1700
Data Index: 3711874 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.9034. Min Act: -0.1700
Data Index: 3361754 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.8721. Min Act: -0.1700
Data Index: 2947135 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.8409. Min Act: -0.1700
Data Index: 3711875 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.8409. Min Act: -0.1700
Data Index: 751679 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.8409. Min Act: -0.1700
Data Index: 3361753 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.8409. Min Act: -0.1700
Data Index: 8028139 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.8096. Min Act: -0.1700
Data Index: 8028140 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.8096. Min Act: -0.1700
Data Index: 5289446 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.7784. Min Act: -0.1700
Data Index: 584647 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.7784. Min Act: -0.1700
Data Index: 4158421 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.7471. Min Act: -0.1700
Data Index: 7824089 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.7471. Min Act: -0.1700
Data Index: 1685849 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.7471. Min Act: -0.1700
Data Index: 4305979 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.7159. Min Act: -0.1700
Data Index: 3711876 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.7159. Min Act: -0.1700
Data Index: 2268654 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.6846. Min Act: -0.1700
Data Index: 1230816 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9659. Min Range: -5.9659
Max Act: 5.6846. Min Act: -0.1700
Data Index: 7747887 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19