Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1962 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.6046. Min Act: -0.1700
Data Index: 3720033 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.5890. Min Act: -0.1700
Data Index: 1677306 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.5420. Min Act: -0.1700
Data Index: 1095346 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.5263. Min Act: -0.1700
Data Index: 3397516 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.5107. Min Act: -0.1700
Data Index: 5367970 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.4950. Min Act: -0.1700
Data Index: 6050757 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.4637. Min Act: -0.1700
Data Index: 723209 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.4480. Min Act: -0.1700
Data Index: 3061567 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.4480. Min Act: -0.1700
Data Index: 5513968 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.4480. Min Act: -0.1700
Data Index: 2576656 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.4010. Min Act: -0.1700
Data Index: 7747315 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.4010. Min Act: -0.1700
Data Index: 3914744 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3853. Min Act: -0.1700
Data Index: 3708280 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3539. Min Act: -0.1700
Data Index: 1189092 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3383. Min Act: -0.1700
Data Index: 7961626 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3539. Min Act: -0.1700
Data Index: 5384518 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3696. Min Act: -0.1700
Data Index: 5834973 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3539. Min Act: -0.1700
Data Index: 851437 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3069. Min Act: -0.1700
Data Index: 1886870 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6046. Min Range: -3.6046
Max Act: 3.3226. Min Act: -0.1700
Data Index: 3760502 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19