Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.4175. Min Act: -0.1700
Data Index: 1942652 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.3550. Min Act: -0.1700
Data Index: 8029547 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.3238. Min Act: -0.1700
Data Index: 7184466 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.3238. Min Act: -0.1700
Data Index: 8454155 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.3238. Min Act: -0.1700
Data Index: 7029760 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.2613. Min Act: -0.1700
Data Index: 7560107 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.2300. Min Act: -0.1700
Data Index: 3751204 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.2300. Min Act: -0.1700
Data Index: 3902614 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.2300. Min Act: -0.1700
Data Index: 2615659 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.2613. Min Act: -0.1700
Data Index: 6972885 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.2300. Min Act: -0.1700
Data Index: 1774611 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1988. Min Act: -0.1700
Data Index: 7937636 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1988. Min Act: -0.1700
Data Index: 7913628 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1988. Min Act: -0.1700
Data Index: 4507742 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1988. Min Act: -0.1700
Data Index: 1054158 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1988. Min Act: -0.1700
Data Index: 7516440 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1988. Min Act: -0.1700
Data Index: 876817 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1988. Min Act: -0.1700
Data Index: 8655058 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1675. Min Act: -0.1700
Data Index: 5874099 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4175. Min Range: -4.4175
Max Act: 4.1675. Min Act: -0.1700
Data Index: 119103 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19