Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0255. Min Range: -8.0255
Max Act: 8.0255. Min Act: -0.1700
Data Index: 8546581 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.6818. Min Act: -0.1700
Data Index: 5448815 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.6505. Min Act: -0.1700
Data Index: 7722586 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.6193. Min Act: -0.1700
Data Index: 698092 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.5255. Min Act: -0.1700
Data Index: 3540681 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.4630. Min Act: -0.1700
Data Index: 7851413 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.3693. Min Act: -0.1700
Data Index: 4912912 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.3693. Min Act: -0.1700
Data Index: 1429438 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.2755. Min Act: -0.1700
Data Index: 701206 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.2755. Min Act: -0.1700
Data Index: 7757531 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.2130. Min Act: -0.1700
Data Index: 7371124 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.1818. Min Act: -0.1700
Data Index: 3560837 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.1818. Min Act: -0.1700
Data Index: 2782199 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.1818. Min Act: -0.1700
Data Index: 3394769 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.1193. Min Act: -0.1700
Data Index: 7936196 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.0880. Min Act: -0.1700
Data Index: 8097255 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.0880. Min Act: -0.1700
Data Index: 2122089 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.0880. Min Act: -0.1700
Data Index: 1544383 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.0255. Min Act: -0.1700
Data Index: 964579 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0255. Min Range: -8.0255
Max Act: 7.0255. Min Act: -0.1700
Data Index: 415121 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19