Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 925 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.9423. Min Act: -0.1700
Data Index: 1159965 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8485. Min Act: -0.1700
Data Index: 828076 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7860. Min Act: -0.1700
Data Index: 1961605 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7860. Min Act: -0.1700
Data Index: 8797301 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7548. Min Act: -0.1700
Data Index: 3756954 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7548. Min Act: -0.1700
Data Index: 7033813 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7235. Min Act: -0.1700
Data Index: 2175593 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7235. Min Act: -0.1700
Data Index: 857985 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7235. Min Act: -0.1700
Data Index: 2898079 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7235. Min Act: -0.1700
Data Index: 2499484 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6923. Min Act: -0.1700
Data Index: 2867366 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6923. Min Act: -0.1700
Data Index: 3794426 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6610. Min Act: -0.1700
Data Index: 1984257 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6298. Min Act: -0.1700
Data Index: 1222226 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6610. Min Act: -0.1700
Data Index: 1229573 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6298. Min Act: -0.1700
Data Index: 8174160 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6610. Min Act: -0.1700
Data Index: 6756945 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6298. Min Act: -0.1700
Data Index: 7960090 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6298. Min Act: -0.1700
Data Index: 6092296 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.6298. Min Act: -0.1700
Data Index: 5100718 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19