Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8737. Min Act: -0.1700
Data Index: 4488709 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8420. Min Act: -0.1700
Data Index: 3606914 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1666974 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8420. Min Act: -0.1700
Data Index: 3163086 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8261. Min Act: -0.1700
Data Index: 4310664 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8261. Min Act: -0.1700
Data Index: 605075 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8261. Min Act: -0.1700
Data Index: 6217522 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8261. Min Act: -0.1700
Data Index: 3004499 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8101. Min Act: -0.1700
Data Index: 8228406 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8101. Min Act: -0.1700
Data Index: 1646842 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8101. Min Act: -0.1700
Data Index: 4618410 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.8101. Min Act: -0.1700
Data Index: 8721087 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7942. Min Act: -0.1700
Data Index: 2620869 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7942. Min Act: -0.1700
Data Index: 1973227 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7942. Min Act: -0.1700
Data Index: 2572116 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7783. Min Act: -0.1700
Data Index: 5033788 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7783. Min Act: -0.1700
Data Index: 826385 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7783. Min Act: -0.1700
Data Index: 397327 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7623. Min Act: -0.1700
Data Index: 5517049 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8737. Min Range: -2.8737
Max Act: 2.7783. Min Act: -0.1700
Data Index: 6242412 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19