Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 182 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.5022. Min Act: -0.1700
Data Index: 2863097 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4709. Min Act: -0.1700
Data Index: 255573 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4396. Min Act: -0.1700
Data Index: 694364 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4239. Min Act: -0.1700
Data Index: 895875 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.4082. Min Act: -0.1700
Data Index: 4824372 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3925. Min Act: -0.1700
Data Index: 2924367 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3768. Min Act: -0.1700
Data Index: 6705821 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3455. Min Act: -0.1700
Data Index: 2345746 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3298. Min Act: -0.1700
Data Index: 2376446 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3455. Min Act: -0.1700
Data Index: 6996088 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3298. Min Act: -0.1700
Data Index: 3373379 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3141. Min Act: -0.1700
Data Index: 4472817 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3141. Min Act: -0.1700
Data Index: 8456660 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3141. Min Act: -0.1700
Data Index: 5796350 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2984. Min Act: -0.1700
Data Index: 1972890 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2984. Min Act: -0.1700
Data Index: 8787831 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.3141. Min Act: -0.1700
Data Index: 5145497 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2984. Min Act: -0.1700
Data Index: 273277 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2827. Min Act: -0.1700
Data Index: 2640865 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5022. Min Range: -3.5022
Max Act: 3.2827. Min Act: -0.1700
Data Index: 1529573 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19