Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5851 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.3268. Min Act: -0.1700
Data Index: 4198440 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.2955. Min Act: -0.1700
Data Index: 1012489 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.2643. Min Act: -0.1700
Data Index: 8650476 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.2330. Min Act: -0.1700
Data Index: 3166855 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.2330. Min Act: -0.1700
Data Index: 6439416 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.2018. Min Act: -0.1700
Data Index: 2640433 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1705. Min Act: -0.1700
Data Index: 6459436 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1705. Min Act: -0.1700
Data Index: 950493 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1705. Min Act: -0.1700
Data Index: 792046 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1705. Min Act: -0.1700
Data Index: 872663 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1705. Min Act: -0.1700
Data Index: 8767675 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1393. Min Act: -0.1700
Data Index: 5754147 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1705. Min Act: -0.1700
Data Index: 4605664 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1393. Min Act: -0.1700
Data Index: 1183994 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1393. Min Act: -0.1700
Data Index: 1370421 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1080. Min Act: -0.1700
Data Index: 7472272 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.0768. Min Act: -0.1700
Data Index: 2269920 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1080. Min Act: -0.1700
Data Index: 3928060 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.1393. Min Act: -0.1700
Data Index: 2812630 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3268. Min Range: -4.3268
Max Act: 4.0768. Min Act: -0.1700
Data Index: 2918857 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19