Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4212960 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9765. Min Act: -0.1700
Data Index: 8442611 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1328. Min Range: -6.1328
Max Act: 6.0078. Min Act: -0.1699
Data Index: 806722 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9765. Min Act: -0.1700
Data Index: 2925607 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.9453. Min Act: -0.1698
Data Index: 7909718 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8828. Min Act: -0.1700
Data Index: 5023157 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8828. Min Act: -0.1700
Data Index: 5106919 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8828. Min Act: -0.1700
Data Index: 442002 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8828. Min Act: -0.1700
Data Index: 6672597 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8515. Min Act: -0.1700
Data Index: 5928224 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8515. Min Act: -0.1700
Data Index: 4984719 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8203. Min Act: -0.1700
Data Index: 3888120 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8203. Min Act: -0.1700
Data Index: 897308 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8203. Min Act: -0.1700
Data Index: 4340918 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8203. Min Act: -0.1700
Data Index: 8287089 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8203. Min Act: -0.1700
Data Index: 6474725 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.8203. Min Act: -0.1700
Data Index: 2861143 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.7578. Min Act: -0.1700
Data Index: 4663486 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.7890. Min Act: -0.1700
Data Index: 7112235 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1328. Min Range: -6.1328
Max Act: 5.7890. Min Act: -0.1700
Data Index: 7161334 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19