Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0951. Min Range: -5.0951
Max Act: 5.0951. Min Act: -0.1700
Data Index: 5276676 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.9076. Min Act: -0.1700
Data Index: 4188558 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8764. Min Act: -0.1700
Data Index: 8525831 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8764. Min Act: -0.1700
Data Index: 469629 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8764. Min Act: -0.1700
Data Index: 5328994 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8139. Min Act: -0.1700
Data Index: 31110 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8451. Min Act: -0.1700
Data Index: 7550899 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8139. Min Act: -0.1700
Data Index: 7803977 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8139. Min Act: -0.1700
Data Index: 7665431 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7826. Min Act: -0.1700
Data Index: 7416899 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7826. Min Act: -0.1700
Data Index: 6244061 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7826. Min Act: -0.1700
Data Index: 8674344 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7826. Min Act: -0.1700
Data Index: 1063867 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.8139. Min Act: -0.1700
Data Index: 2578887 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7514. Min Act: -0.1700
Data Index: 2097162 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7826. Min Act: -0.1700
Data Index: 8796637 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7826. Min Act: -0.1700
Data Index: 410258 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7826. Min Act: -0.1700
Data Index: 2212385 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7201. Min Act: -0.1700
Data Index: 5092152 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0951. Min Range: -5.0951
Max Act: 4.7514. Min Act: -0.1700
Data Index: 7618758 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19