Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.4481. Min Act: -0.1700
Data Index: 803978 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.2606. Min Act: -0.1700
Data Index: 4278606 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.2919. Min Act: -0.1700
Data Index: 3703665 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.2919. Min Act: -0.1700
Data Index: 6668621 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.2294. Min Act: -0.1700
Data Index: 1930559 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.2606. Min Act: -0.1700
Data Index: 713260 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.2606. Min Act: -0.1700
Data Index: 2139660 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.2294. Min Act: -0.1700
Data Index: 2944220 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1981. Min Act: -0.1700
Data Index: 5774278 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1981. Min Act: -0.1700
Data Index: 5734665 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1981. Min Act: -0.1700
Data Index: 987359 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1981. Min Act: -0.1700
Data Index: 3396602 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1981. Min Act: -0.1700
Data Index: 3481423 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1668. Min Act: -0.1700
Data Index: 459477 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1668. Min Act: -0.1700
Data Index: 7945847 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1981. Min Act: -0.1700
Data Index: 1023168 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1668. Min Act: -0.1700
Data Index: 1194122 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1668. Min Act: -0.1700
Data Index: 5901208 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1668. Min Act: -0.1700
Data Index: 3142175 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4481. Min Range: -4.4481
Max Act: 4.1668. Min Act: -0.1700
Data Index: 1046708 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19