Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.3726. Min Act: -0.1700
Data Index: 1257859 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.2476. Min Act: -0.1700
Data Index: 4954062 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.1851. Min Act: -0.1700
Data Index: 325464 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.1851. Min Act: -0.1700
Data Index: 2980607 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.1226. Min Act: -0.1700
Data Index: 7713022 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.1226. Min Act: -0.1700
Data Index: 1315068 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.0601. Min Act: -0.1700
Data Index: 4394796 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.0601. Min Act: -0.1700
Data Index: 6391631 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3726. Min Range: -8.3726
Max Act: 8.0601. Min Act: -0.1700
Data Index: 8736508 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.9976. Min Act: -0.1700
Data Index: 5285482 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.9663. Min Act: -0.1700
Data Index: 7545215 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.9976. Min Act: -0.1700
Data Index: 6731280 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.9663. Min Act: -0.1700
Data Index: 7016170 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.9663. Min Act: -0.1700
Data Index: 5452828 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.9351. Min Act: -0.1700
Data Index: 5706933 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.8726. Min Act: -0.1700
Data Index: 1140082 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.8413. Min Act: -0.1700
Data Index: 2200649 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.8413. Min Act: -0.1700
Data Index: 2281518 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.8101. Min Act: -0.1700
Data Index: 1733685 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3726. Min Range: -8.3726
Max Act: 7.8413. Min Act: -0.1700
Data Index: 7599638 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19