Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 534 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2494. Min Range: -6.2494
Max Act: 6.2494. Min Act: -0.1700
Data Index: 7583089 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2494. Min Range: -6.2494
Max Act: 6.1244. Min Act: -0.1700
Data Index: 6871956 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2494. Min Range: -6.2494
Max Act: 6.0931. Min Act: -0.1700
Data Index: 2942004 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2494. Min Range: -6.2494
Max Act: 6.0619. Min Act: -0.1700
Data Index: 3228541 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2494. Min Range: -6.2494
Max Act: 6.0619. Min Act: -0.1700
Data Index: 998951 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2494. Min Range: -6.2494
Max Act: 6.0619. Min Act: -0.1700
Data Index: 2922164 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.8744. Min Act: -0.1700
Data Index: 7387540 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.9056. Min Act: -0.1700
Data Index: 942285 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.8431. Min Act: -0.1700
Data Index: 4135022 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.8431. Min Act: -0.1700
Data Index: 7650172 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.8431. Min Act: -0.1700
Data Index: 254970 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.8119. Min Act: -0.1700
Data Index: 937032 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.8119. Min Act: -0.1700
Data Index: 5504841 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.7806. Min Act: -0.1700
Data Index: 752885 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.7806. Min Act: -0.1700
Data Index: 2824009 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.7806. Min Act: -0.1700
Data Index: 8175425 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.7494. Min Act: -0.1700
Data Index: 3076831 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.7181. Min Act: -0.1700
Data Index: 6055355 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.7494. Min Act: -0.1700
Data Index: 8140401 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2494. Min Range: -6.2494
Max Act: 5.6869. Min Act: -0.1700
Data Index: 2969762 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19