Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2953 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.2435. Min Act: -0.1700
Data Index: 3405290 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.2122. Min Act: -0.1700
Data Index: 2740257 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.1810. Min Act: -0.1700
Data Index: 7447336 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.1497. Min Act: -0.1700
Data Index: 7447325 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.1497. Min Act: -0.1700
Data Index: 6714144 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.0560. Min Act: -0.1700
Data Index: 6339732 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.0872. Min Act: -0.1700
Data Index: 444261 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.0872. Min Act: -0.1700
Data Index: 6835523 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.0247. Min Act: -0.1700
Data Index: 7447338 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2435. Min Range: -4.2435
Max Act: 4.0247. Min Act: -0.1700
Data Index: 3348480 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9934. Min Act: -0.1700
Data Index: 8646088 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9934. Min Act: -0.1700
Data Index: 7062456 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9934. Min Act: -0.1700
Data Index: 4353330 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9622. Min Act: -0.1700
Data Index: 8569917 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9622. Min Act: -0.1700
Data Index: 7447340 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9622. Min Act: -0.1700
Data Index: 7447339 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9622. Min Act: -0.1700
Data Index: 2285262 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9622. Min Act: -0.1700
Data Index: 7447357 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9622. Min Act: -0.1700
Data Index: 7447330 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2435. Min Range: -4.2435
Max Act: 3.9934. Min Act: -0.1700
Data Index: 7447329 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19