Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1203. Min Range: -5.1203
Max Act: 5.1203. Min Act: -0.1700
Data Index: 5018434 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1203. Min Range: -5.1203
Max Act: 5.0578. Min Act: -0.1700
Data Index: 4767692 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.9953. Min Act: -0.1700
Data Index: 213945 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.9640. Min Act: -0.1700
Data Index: 8583756 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.9328. Min Act: -0.1700
Data Index: 7361982 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.9328. Min Act: -0.1700
Data Index: 8521039 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.9015. Min Act: -0.1700
Data Index: 271122 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8703. Min Act: -0.1700
Data Index: 3611228 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8703. Min Act: -0.1700
Data Index: 4918779 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8390. Min Act: -0.1700
Data Index: 876997 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.9015. Min Act: -0.1700
Data Index: 6718341 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8703. Min Act: -0.1700
Data Index: 3490934 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8390. Min Act: -0.1700
Data Index: 2352955 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8390. Min Act: -0.1700
Data Index: 1111917 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8703. Min Act: -0.1700
Data Index: 7454415 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8390. Min Act: -0.1700
Data Index: 6399615 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8078. Min Act: -0.1700
Data Index: 6283628 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.7765. Min Act: -0.1700
Data Index: 233259 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8078. Min Act: -0.1700
Data Index: 3912068 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1203. Min Range: -5.1203
Max Act: 4.8078. Min Act: -0.1700
Data Index: 1055950 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19