Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1676. Min Range: -4.1676
Max Act: 4.1676. Min Act: -0.1700
Data Index: 2570203 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1676. Min Range: -4.1676
Max Act: 4.1051. Min Act: -0.1700
Data Index: 3591135 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.9176. Min Act: -0.1700
Data Index: 2415871 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.8707. Min Act: -0.1700
Data Index: 5807126 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.8707. Min Act: -0.1700
Data Index: 4514924 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.8081. Min Act: -0.1700
Data Index: 6695747 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7925. Min Act: -0.1700
Data Index: 3805367 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7612. Min Act: -0.1700
Data Index: 4069097 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7456. Min Act: -0.1700
Data Index: 8452402 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7612. Min Act: -0.1700
Data Index: 7437280 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7612. Min Act: -0.1700
Data Index: 2084319 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7612. Min Act: -0.1700
Data Index: 1064658 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7456. Min Act: -0.1700
Data Index: 3699324 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7299. Min Act: -0.1700
Data Index: 7568188 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.6987. Min Act: -0.1700
Data Index: 255834 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.7299. Min Act: -0.1700
Data Index: 432576 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.6830. Min Act: -0.1700
Data Index: 4950610 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.6517. Min Act: -0.1700
Data Index: 1719130 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.6674. Min Act: -0.1700
Data Index: 1580776 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1676. Min Range: -4.1676
Max Act: 3.6361. Min Act: -0.1700
Data Index: 4100110 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19