Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1831. Min Range: -5.1831
Max Act: 5.1831. Min Act: -0.1700
Data Index: 786932 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1831. Min Range: -5.1831
Max Act: 5.1518. Min Act: -0.1700
Data Index: 4877022 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1831. Min Range: -5.1831
Max Act: 5.1206. Min Act: -0.1700
Data Index: 418118 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1831. Min Range: -5.1831
Max Act: 5.0893. Min Act: -0.1700
Data Index: 2780118 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1831. Min Range: -5.1831
Max Act: 5.0893. Min Act: -0.1700
Data Index: 1265611 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.9643. Min Act: -0.1700
Data Index: 6646825 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.9018. Min Act: -0.1700
Data Index: 5856549 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.8393. Min Act: -0.1700
Data Index: 4918696 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.8393. Min Act: -0.1700
Data Index: 3346188 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.8081. Min Act: -0.1700
Data Index: 3033945 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.8081. Min Act: -0.1700
Data Index: 835699 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.8081. Min Act: -0.1700
Data Index: 1251606 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.8081. Min Act: -0.1700
Data Index: 835701 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.7768. Min Act: -0.1700
Data Index: 2158721 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.7456. Min Act: -0.1700
Data Index: 1767734 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.7143. Min Act: -0.1700
Data Index: 2214778 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.7143. Min Act: -0.1700
Data Index: 4427602 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.7143. Min Act: -0.1700
Data Index: 1684300 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.7143. Min Act: -0.1700
Data Index: 3144692 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1831. Min Range: -5.1831
Max Act: 4.7143. Min Act: -0.1700
Data Index: 4288775 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19