Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.9581. Min Act: -0.1700
Data Index: 7888065 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8956. Min Act: -0.1700
Data Index: 3975789 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8956. Min Act: -0.1700
Data Index: 6967814 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8956. Min Act: -0.1700
Data Index: 3573360 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8643. Min Act: -0.1700
Data Index: 6132508 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8956. Min Act: -0.1700
Data Index: 5686160 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8956. Min Act: -0.1700
Data Index: 7198388 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8956. Min Act: -0.1700
Data Index: 4787940 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.8331. Min Act: -0.1700
Data Index: 5048088 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7706. Min Act: -0.1700
Data Index: 3889519 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7706. Min Act: -0.1700
Data Index: 6338875 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7706. Min Act: -0.1700
Data Index: 4313428 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7081. Min Act: -0.1700
Data Index: 2586983 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7393. Min Act: -0.1700
Data Index: 7326428 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7393. Min Act: -0.1700
Data Index: 373798 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7393. Min Act: -0.1700
Data Index: 46742 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7393. Min Act: -0.1700
Data Index: 1588148 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7393. Min Act: -0.1700
Data Index: 1608584 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7081. Min Act: -0.1700
Data Index: 3671867 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9581. Min Range: -4.9581
Max Act: 4.7393. Min Act: -0.1700
Data Index: 1948783 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19