Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4713 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.7739. Min Act: -0.1700
Data Index: 8487472 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.7114. Min Act: -0.1700
Data Index: 7444985 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.6801. Min Act: -0.1700
Data Index: 5099512 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.6489. Min Act: -0.1700
Data Index: 8537218 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.6489. Min Act: -0.1700
Data Index: 5834193 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.5864. Min Act: -0.1700
Data Index: 4890616 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.5551. Min Act: -0.1700
Data Index: 1892302 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.5551. Min Act: -0.1700
Data Index: 8306562 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.5551. Min Act: -0.1700
Data Index: 5436724 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.5239. Min Act: -0.1700
Data Index: 6754338 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.5239. Min Act: -0.1700
Data Index: 4648922 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4926. Min Act: -0.1700
Data Index: 8158644 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4926. Min Act: -0.1700
Data Index: 7493162 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4926. Min Act: -0.1700
Data Index: 6198483 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4614. Min Act: -0.1700
Data Index: 2022801 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4614. Min Act: -0.1700
Data Index: 291107 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4614. Min Act: -0.1700
Data Index: 4739779 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4614. Min Act: -0.1700
Data Index: 3665111 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4614. Min Act: -0.1700
Data Index: 5099516 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7739. Min Range: -5.7739
Max Act: 5.4614. Min Act: -0.1700
Data Index: 6304352 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19