Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5220 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.3125. Min Act: -0.1700
Data Index: 6139164 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.2812. Min Act: -0.1700
Data Index: 8207816 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.2812. Min Act: -0.1700
Data Index: 4097701 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.2500. Min Act: -0.1700
Data Index: 2279021 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.2500. Min Act: -0.1700
Data Index: 5577306 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.2187. Min Act: -0.1700
Data Index: 3633950 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1875. Min Act: -0.1700
Data Index: 5063835 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1875. Min Act: -0.1700
Data Index: 4154988 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1875. Min Act: -0.1700
Data Index: 2562108 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1875. Min Act: -0.1700
Data Index: 5577959 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1875. Min Act: -0.1700
Data Index: 5825253 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1875. Min Act: -0.1700
Data Index: 2929377 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1250. Min Act: -0.1700
Data Index: 3526461 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1250. Min Act: -0.1700
Data Index: 6486562 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.0937. Min Act: -0.1700
Data Index: 2637824 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1250. Min Act: -0.1700
Data Index: 1081839 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.1250. Min Act: -0.1700
Data Index: 597943 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.0625. Min Act: -0.1700
Data Index: 6459890 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.0625. Min Act: -0.1700
Data Index: 5092815 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3125. Min Range: -5.3125
Max Act: 5.0937. Min Act: -0.1700
Data Index: 8026710 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19