Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.7727. Min Act: -0.1700
Data Index: 5529750 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6768. Min Act: -0.1700
Data Index: 6393457 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6608. Min Act: -0.1700
Data Index: 1124474 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6448. Min Act: -0.1700
Data Index: 604023 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6448. Min Act: -0.1700
Data Index: 7765203 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6287. Min Act: -0.1700
Data Index: 554005 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6287. Min Act: -0.1700
Data Index: 3515325 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6287. Min Act: -0.1700
Data Index: 3629932 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6287. Min Act: -0.1700
Data Index: 3942760 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6287. Min Act: -0.1700
Data Index: 4394324 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6126. Min Act: -0.1700
Data Index: 5333266 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6126. Min Act: -0.1700
Data Index: 8277692 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6126. Min Act: -0.1700
Data Index: 5515966 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6126. Min Act: -0.1700
Data Index: 3515323 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6126. Min Act: -0.1700
Data Index: 2522176 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6126. Min Act: -0.1700
Data Index: 1287528 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.6126. Min Act: -0.1700
Data Index: 261482 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.5804. Min Act: -0.1700
Data Index: 6651644 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.5965. Min Act: -0.1700
Data Index: 7252587 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7727. Min Range: -2.7727
Max Act: 2.5965. Min Act: -0.1700
Data Index: 7316562 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19