Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.4295. Min Act: -0.1700
Data Index: 2203664 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2732. Min Act: -0.1700
Data Index: 4645014 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2732. Min Act: -0.1700
Data Index: 8290553 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2420. Min Act: -0.1700
Data Index: 1468255 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2420. Min Act: -0.1700
Data Index: 6498954 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2107. Min Act: -0.1700
Data Index: 6563963 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2107. Min Act: -0.1700
Data Index: 8401637 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2420. Min Act: -0.1700
Data Index: 7394271 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.2107. Min Act: -0.1700
Data Index: 6664274 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1794. Min Act: -0.1700
Data Index: 6519989 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1794. Min Act: -0.1700
Data Index: 5065987 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 3838372 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 797266 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1921581 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 2000862 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1169. Min Act: -0.1700
Data Index: 6919498 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 4476649 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 3154945 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 8766670 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4295. Min Range: -4.4295
Max Act: 4.1482. Min Act: -0.1700
Data Index: 2355997 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19