Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3923 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2778. Min Range: -8.2778
Max Act: 8.2778. Min Act: -0.1700
Data Index: 3895447 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2778. Min Range: -8.2778
Max Act: 8.2778. Min Act: -0.1700
Data Index: 5378361 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2778. Min Range: -8.2778
Max Act: 8.2466. Min Act: -0.1700
Data Index: 6371046 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2778. Min Range: -8.2778
Max Act: 8.0278. Min Act: -0.1700
Data Index: 4076758 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.9966. Min Act: -0.1700
Data Index: 6371045 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.9028. Min Act: -0.1700
Data Index: 3677140 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.9341. Min Act: -0.1700
Data Index: 6371033 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.9028. Min Act: -0.1700
Data Index: 3969813 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.8716. Min Act: -0.1700
Data Index: 2698826 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.8091. Min Act: -0.1700
Data Index: 3232142 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.7466. Min Act: -0.1700
Data Index: 6371037 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.7466. Min Act: -0.1700
Data Index: 7241467 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.6841. Min Act: -0.1700
Data Index: 6371038 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.6841. Min Act: -0.1700
Data Index: 6614630 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.6841. Min Act: -0.1700
Data Index: 2683160 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.6216. Min Act: -0.1700
Data Index: 6614627 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.6528. Min Act: -0.1700
Data Index: 6837300 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.6841. Min Act: -0.1700
Data Index: 8309193 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.6841. Min Act: -0.1700
Data Index: 3106951 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2778. Min Range: -8.2778
Max Act: 7.5591. Min Act: -0.1700
Data Index: 6192317 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19