Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 940 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0845. Min Range: -4.0845
Max Act: 4.0845. Min Act: -0.1700
Data Index: 1994970 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.9908. Min Act: -0.1700
Data Index: 282676 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.9595. Min Act: -0.1700
Data Index: 3508385 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.9282. Min Act: -0.1700
Data Index: 1337353 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.9126. Min Act: -0.1700
Data Index: 2429428 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8501. Min Act: -0.1700
Data Index: 1495710 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8501. Min Act: -0.1700
Data Index: 4579954 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8501. Min Act: -0.1700
Data Index: 4545603 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8344. Min Act: -0.1700
Data Index: 2429287 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8188. Min Act: -0.1700
Data Index: 6752787 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8188. Min Act: -0.1700
Data Index: 4401819 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7719. Min Act: -0.1700
Data Index: 3702538 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7875. Min Act: -0.1700
Data Index: 1744919 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7875. Min Act: -0.1700
Data Index: 3756123 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7562. Min Act: -0.1700
Data Index: 4069034 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7562. Min Act: -0.1700
Data Index: 6256140 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7562. Min Act: -0.1700
Data Index: 1087160 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7406. Min Act: -0.1700
Data Index: 4395148 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7562. Min Act: -0.1700
Data Index: 8122227 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7406. Min Act: -0.1700
Data Index: 2342108 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19