Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0360. Min Range: -5.0360
Max Act: 5.0360. Min Act: -0.1700
Data Index: 535848 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.9422. Min Act: -0.1700
Data Index: 8169267 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.8485. Min Act: -0.1700
Data Index: 1769470 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.8485. Min Act: -0.1700
Data Index: 4848126 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.8485. Min Act: -0.1700
Data Index: 8176624 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.8485. Min Act: -0.1700
Data Index: 5218997 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.8172. Min Act: -0.1700
Data Index: 3266839 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7860. Min Act: -0.1700
Data Index: 6491114 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7860. Min Act: -0.1700
Data Index: 4286959 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7547. Min Act: -0.1700
Data Index: 4117654 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7547. Min Act: -0.1700
Data Index: 3912155 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7547. Min Act: -0.1700
Data Index: 5388463 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7235. Min Act: -0.1700
Data Index: 2044739 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7235. Min Act: -0.1700
Data Index: 4930512 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.6922. Min Act: -0.1700
Data Index: 6317935 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.6922. Min Act: -0.1700
Data Index: 567913 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.6922. Min Act: -0.1700
Data Index: 4996639 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.7235. Min Act: -0.1700
Data Index: 7050917 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.6610. Min Act: -0.1700
Data Index: 5774374 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0360. Min Range: -5.0360
Max Act: 4.6610. Min Act: -0.1700
Data Index: 4901676 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19