Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.4403. Min Act: -0.1700
Data Index: 5409374 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.1590. Min Act: -0.1700
Data Index: 3474042 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.0965. Min Act: -0.1700
Data Index: 8577041 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.0340. Min Act: -0.1700
Data Index: 4159002 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.0340. Min Act: -0.1700
Data Index: 3588546 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.0027. Min Act: -0.1700
Data Index: 1064834 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.0027. Min Act: -0.1700
Data Index: 336478 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.9714. Min Act: -0.1700
Data Index: 5980450 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4403. Min Range: -4.4403
Max Act: 4.0027. Min Act: -0.1700
Data Index: 7716623 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.9714. Min Act: -0.1700
Data Index: 5969020 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.9558. Min Act: -0.1700
Data Index: 3154393 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.9402. Min Act: -0.1700
Data Index: 7141945 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.9402. Min Act: -0.1700
Data Index: 6369498 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.9089. Min Act: -0.1700
Data Index: 447031 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.9246. Min Act: -0.1700
Data Index: 6973853 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.8777. Min Act: -0.1700
Data Index: 5462832 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.8777. Min Act: -0.1700
Data Index: 6039243 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.8777. Min Act: -0.1700
Data Index: 568540 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.8464. Min Act: -0.1700
Data Index: 2888205 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4403. Min Range: -4.4403
Max Act: 3.8620. Min Act: -0.1700
Data Index: 8137602 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19