Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0802. Min Range: -5.0802
Max Act: 5.0802. Min Act: -0.1700
Data Index: 8781186 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.7989. Min Act: -0.1700
Data Index: 7779986 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.7364. Min Act: -0.1700
Data Index: 7991480 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.7364. Min Act: -0.1700
Data Index: 3641730 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.7364. Min Act: -0.1700
Data Index: 1039060 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6739. Min Act: -0.1700
Data Index: 948129 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.7052. Min Act: -0.1700
Data Index: 8818808 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6739. Min Act: -0.1700
Data Index: 7797428 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6739. Min Act: -0.1700
Data Index: 1815552 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6739. Min Act: -0.1700
Data Index: 3167275 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6739. Min Act: -0.1700
Data Index: 6541532 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6427. Min Act: -0.1700
Data Index: 2663659 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6427. Min Act: -0.1700
Data Index: 5956494 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6427. Min Act: -0.1700
Data Index: 4137188 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6427. Min Act: -0.1700
Data Index: 6507956 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6114. Min Act: -0.1700
Data Index: 1382128 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6114. Min Act: -0.1700
Data Index: 5108819 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6427. Min Act: -0.1700
Data Index: 2700054 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6114. Min Act: -0.1700
Data Index: 2039155 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0802. Min Range: -5.0802
Max Act: 4.6114. Min Act: -0.1700
Data Index: 8371138 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19