Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5789 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.2679. Min Act: -0.1700
Data Index: 4981441 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.2366. Min Act: -0.1700
Data Index: 5281701 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.1741. Min Act: -0.1700
Data Index: 3033721 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.1116. Min Act: -0.1700
Data Index: 2592139 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0491. Min Act: -0.1700
Data Index: 2716158 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.1116. Min Act: -0.1700
Data Index: 5141850 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0491. Min Act: -0.1700
Data Index: 5019656 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0491. Min Act: -0.1700
Data Index: 4397403 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0179. Min Act: -0.1700
Data Index: 7481657 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0179. Min Act: -0.1700
Data Index: 2693684 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0179. Min Act: -0.1700
Data Index: 6992944 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0179. Min Act: -0.1700
Data Index: 5388414 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2679. Min Range: -5.2679
Max Act: 5.0179. Min Act: -0.1700
Data Index: 6992943 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2679. Min Range: -5.2679
Max Act: 4.9866. Min Act: -0.1700
Data Index: 4771292 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2679. Min Range: -5.2679
Max Act: 4.9866. Min Act: -0.1700
Data Index: 645126 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2679. Min Range: -5.2679
Max Act: 4.9866. Min Act: -0.1700
Data Index: 1634248 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2679. Min Range: -5.2679
Max Act: 4.9866. Min Act: -0.1700
Data Index: 8812711 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2679. Min Range: -5.2679
Max Act: 4.9554. Min Act: -0.1700
Data Index: 2199954 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2679. Min Range: -5.2679
Max Act: 4.9554. Min Act: -0.1700
Data Index: 4020486 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2679. Min Range: -5.2679
Max Act: 4.9554. Min Act: -0.1700
Data Index: 1336403 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19