Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0457. Min Range: -5.0457
Max Act: 5.0457. Min Act: -0.1700
Data Index: 4077865 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.8582. Min Act: -0.1700
Data Index: 3811775 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.8269. Min Act: -0.1700
Data Index: 3811764 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.7957. Min Act: -0.1700
Data Index: 4077869 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.7644. Min Act: -0.1700
Data Index: 200655 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.7644. Min Act: -0.1700
Data Index: 1429242 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.7332. Min Act: -0.1700
Data Index: 342563 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.7019. Min Act: -0.1700
Data Index: 3811767 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.7019. Min Act: -0.1700
Data Index: 7674413 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6707. Min Act: -0.1700
Data Index: 2291940 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6394. Min Act: -0.1700
Data Index: 2400199 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6707. Min Act: -0.1700
Data Index: 4352488 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6707. Min Act: -0.1700
Data Index: 3693845 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6082. Min Act: -0.1700
Data Index: 4332609 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6394. Min Act: -0.1700
Data Index: 6326041 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6394. Min Act: -0.1700
Data Index: 3475128 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6394. Min Act: -0.1700
Data Index: 821499 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6394. Min Act: -0.1700
Data Index: 4262431 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.5769. Min Act: -0.1700
Data Index: 703888 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0457. Min Range: -5.0457
Max Act: 4.6082. Min Act: -0.1700
Data Index: 189722 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19