Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5637 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.6747. Min Act: -0.1700
Data Index: 7719427 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.1747. Min Act: -0.1700
Data Index: 4431612 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.2060. Min Act: -0.1700
Data Index: 189316 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.1747. Min Act: -0.1700
Data Index: 7453969 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.1747. Min Act: -0.1700
Data Index: 7389519 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.1435. Min Act: -0.1700
Data Index: 8443524 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.0810. Min Act: -0.1700
Data Index: 7851382 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.0497. Min Act: -0.1700
Data Index: 7069248 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.0185. Min Act: -0.1700
Data Index: 4550369 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.0185. Min Act: -0.1700
Data Index: 2772805 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.0185. Min Act: -0.1700
Data Index: 5161090 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6747. Min Range: -5.6747
Max Act: 5.0497. Min Act: -0.1700
Data Index: 4609220 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.9872. Min Act: -0.1700
Data Index: 3432518 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 3811239 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 2022606 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.9560. Min Act: -0.1700
Data Index: 5138337 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.9560. Min Act: -0.1700
Data Index: 5723427 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.8935. Min Act: -0.1700
Data Index: 7000248 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 6147377 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6747. Min Range: -5.6747
Max Act: 4.8935. Min Act: -0.1700
Data Index: 583309 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19