Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3844 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2853. Min Range: -6.2853
Max Act: 6.2853. Min Act: -0.1700
Data Index: 4148742 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.9416. Min Act: -0.1700
Data Index: 7704536 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.4416. Min Act: -0.1700
Data Index: 3161131 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.4728. Min Act: -0.1700
Data Index: 2952430 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.4416. Min Act: -0.1700
Data Index: 4858528 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.3791. Min Act: -0.1700
Data Index: 1338150 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.2541. Min Act: -0.1700
Data Index: 5476846 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.2541. Min Act: -0.1700
Data Index: 4608508 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.2228. Min Act: -0.1700
Data Index: 6259978 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.2228. Min Act: -0.1700
Data Index: 5909256 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1916. Min Act: -0.1700
Data Index: 6751295 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.2228. Min Act: -0.1700
Data Index: 7704537 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1916. Min Act: -0.1700
Data Index: 3966894 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1291. Min Act: -0.1700
Data Index: 7704535 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1291. Min Act: -0.1700
Data Index: 8805125 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1291. Min Act: -0.1700
Data Index: 3070839 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1603. Min Act: -0.1700
Data Index: 2564752 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1291. Min Act: -0.1700
Data Index: 6820040 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.1291. Min Act: -0.1700
Data Index: 2737090 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2853. Min Range: -6.2853
Max Act: 5.0978. Min Act: -0.1700
Data Index: 4445881 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19