Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1910 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3153. Min Range: -11.3153
Max Act: 11.3153. Min Act: -0.1700
Data Index: 335503 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3153. Min Range: -11.3153
Max Act: 11.1278. Min Act: -0.1700
Data Index: 268000 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3153. Min Range: -11.3153
Max Act: 11.0028. Min Act: -0.1700
Data Index: 3241172 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.9403. Min Act: -0.1700
Data Index: 6900594 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.9403. Min Act: -0.1700
Data Index: 5650506 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.9403. Min Act: -0.1700
Data Index: 8818741 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.9403. Min Act: -0.1700
Data Index: 2499684 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.9403. Min Act: -0.1700
Data Index: 4006421 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.9403. Min Act: -0.1700
Data Index: 4011441 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.9403. Min Act: -0.1700
Data Index: 7345129 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.8778. Min Act: -0.1700
Data Index: 4478147 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.7528. Min Act: -0.1700
Data Index: 2865204 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.8153. Min Act: -0.1700
Data Index: 5991328 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.8153. Min Act: -0.1700
Data Index: 3001898 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.8153. Min Act: -0.1700
Data Index: 136757 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.7528. Min Act: -0.1700
Data Index: 8464632 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.7528. Min Act: -0.1700
Data Index: 4654195 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.7528. Min Act: -0.1700
Data Index: 6673826 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.7528. Min Act: -0.1700
Data Index: 228189 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3153. Min Range: -11.3153
Max Act: 10.7528. Min Act: -0.1700
Data Index: 2708983 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19