Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2765 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.5022. Min Act: -0.1700
Data Index: 7611216 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.4372. Min Act: -0.1700
Data Index: 6352233 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.3883. Min Act: -0.1700
Data Index: 3618989 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.3883. Min Act: -0.1700
Data Index: 5655234 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.3720. Min Act: -0.1700
Data Index: 8632889 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.3064. Min Act: -0.1700
Data Index: 6740390 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.2569. Min Act: -0.1700
Data Index: 2424369 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.2239. Min Act: -0.1700
Data Index: 1212453 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.2404. Min Act: -0.1700
Data Index: 1071256 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.2073. Min Act: -0.1700
Data Index: 8778072 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.2073. Min Act: -0.1700
Data Index: 5611489 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1741. Min Act: -0.1700
Data Index: 1164328 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1907. Min Act: -0.1700
Data Index: 8413867 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.2073. Min Act: -0.1700
Data Index: 8173912 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1741. Min Act: -0.1700
Data Index: 7653534 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1741. Min Act: -0.1700
Data Index: 7056480 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1574. Min Act: -0.1700
Data Index: 3980733 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1574. Min Act: -0.1700
Data Index: 7783300 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1574. Min Act: -0.1700
Data Index: 613768 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5022. Min Range: -2.5022
Max Act: 2.1408. Min Act: -0.1700
Data Index: 2766647 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19