Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6092 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8847. Min Range: -8.8847
Max Act: 8.8847. Min Act: -0.1700
Data Index: 4168458 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8847. Min Range: -8.8847
Max Act: 8.4472. Min Act: -0.1700
Data Index: 184023 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8847. Min Range: -8.8847
Max Act: 8.4472. Min Act: -0.1700
Data Index: 1005456 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8847. Min Range: -8.8847
Max Act: 8.1347. Min Act: -0.1700
Data Index: 6138990 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8847. Min Range: -8.8847
Max Act: 8.1347. Min Act: -0.1700
Data Index: 7860104 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8847. Min Range: -8.8847
Max Act: 8.0097. Min Act: -0.1700
Data Index: 7889813 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8847. Min Range: -8.8847
Max Act: 8.0097. Min Act: -0.1700
Data Index: 8580255 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.9472. Min Act: -0.1700
Data Index: 2221084 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.9472. Min Act: -0.1700
Data Index: 1010804 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.9472. Min Act: -0.1700
Data Index: 37904 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.8847. Min Act: -0.1700
Data Index: 1254386 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.9472. Min Act: -0.1700
Data Index: 7701669 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.9160. Min Act: -0.1700
Data Index: 7736386 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.9160. Min Act: -0.1700
Data Index: 5382613 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.8535. Min Act: -0.1700
Data Index: 6130435 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.8535. Min Act: -0.1700
Data Index: 886743 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.8535. Min Act: -0.1700
Data Index: 6970012 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.8222. Min Act: -0.1700
Data Index: 4450140 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.7910. Min Act: -0.1700
Data Index: 1165028 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8847. Min Range: -8.8847
Max Act: 7.8222. Min Act: -0.1700
Data Index: 6413956 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19