Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.8244. Min Act: -0.1700
Data Index: 6968556 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.7306. Min Act: -0.1700
Data Index: 178380 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6994. Min Act: -0.1700
Data Index: 6260350 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6681. Min Act: -0.1700
Data Index: 2642044 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6681. Min Act: -0.1700
Data Index: 4190553 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6369. Min Act: -0.1700
Data Index: 1641509 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6369. Min Act: -0.1700
Data Index: 8475461 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6056. Min Act: -0.1700
Data Index: 759098 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6681. Min Act: -0.1700
Data Index: 2597429 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6056. Min Act: -0.1700
Data Index: 2363263 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6056. Min Act: -0.1700
Data Index: 5786197 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.5744. Min Act: -0.1700
Data Index: 982614 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.5744. Min Act: -0.1700
Data Index: 817345 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6056. Min Act: -0.1700
Data Index: 1364461 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.5431. Min Act: -0.1700
Data Index: 491179 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.6056. Min Act: -0.1700
Data Index: 2460587 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.5431. Min Act: -0.1700
Data Index: 403156 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.5431. Min Act: -0.1700
Data Index: 1056179 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.5431. Min Act: -0.1700
Data Index: 164063 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8244. Min Range: -5.8244
Max Act: 5.5431. Min Act: -0.1700
Data Index: 8081045 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19