Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5847 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.7583. Min Act: -0.1700
Data Index: 827415 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.6958. Min Act: -0.1700
Data Index: 1301774 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.6958. Min Act: -0.1700
Data Index: 6374744 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.6333. Min Act: -0.1700
Data Index: 7093667 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.3833. Min Act: -0.1700
Data Index: 5736731 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.3208. Min Act: -0.1700
Data Index: 7747984 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.1333. Min Act: -0.1700
Data Index: 634187 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.0708. Min Act: -0.1700
Data Index: 3295811 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.0708. Min Act: -0.1700
Data Index: 7714179 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.0708. Min Act: -0.1700
Data Index: 992198 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.0083. Min Act: -0.1700
Data Index: 1715793 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.0083. Min Act: -0.1700
Data Index: 1633322 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7583. Min Range: -9.7583
Max Act: 9.0083. Min Act: -0.1700
Data Index: 8247666 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7583. Min Range: -9.7583
Max Act: 8.9458. Min Act: -0.1700
Data Index: 4901000 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7583. Min Range: -9.7583
Max Act: 8.8833. Min Act: -0.1700
Data Index: 3710743 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7583. Min Range: -9.7583
Max Act: 8.9458. Min Act: -0.1700
Data Index: 6668487 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7583. Min Range: -9.7583
Max Act: 8.9458. Min Act: -0.1700
Data Index: 2416398 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7583. Min Range: -9.7583
Max Act: 8.8833. Min Act: -0.1700
Data Index: 1977362 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7583. Min Range: -9.7583
Max Act: 8.8833. Min Act: -0.1700
Data Index: 3075080 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7583. Min Range: -9.7583
Max Act: 8.8833. Min Act: -0.1700
Data Index: 6564626 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19