Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 899 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1396. Min Range: -4.1396
Max Act: 4.1396. Min Act: -0.1700
Data Index: 2722314 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.9677. Min Act: -0.1700
Data Index: 1303856 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.9052. Min Act: -0.1700
Data Index: 876714 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8583. Min Act: -0.1700
Data Index: 454625 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8114. Min Act: -0.1700
Data Index: 3073538 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8426. Min Act: -0.1700
Data Index: 4392734 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8270. Min Act: -0.1700
Data Index: 2186311 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8270. Min Act: -0.1700
Data Index: 3531379 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8583. Min Act: -0.1700
Data Index: 6018054 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8114. Min Act: -0.1700
Data Index: 5371789 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8270. Min Act: -0.1700
Data Index: 1037784 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8114. Min Act: -0.1700
Data Index: 1309353 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.7801. Min Act: -0.1700
Data Index: 699165 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.7645. Min Act: -0.1700
Data Index: 7936858 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.8114. Min Act: -0.1700
Data Index: 382825 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.7488. Min Act: -0.1700
Data Index: 4539164 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.7175. Min Act: -0.1700
Data Index: 3073552 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.7332. Min Act: -0.1700
Data Index: 7399044 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.7019. Min Act: -0.1700
Data Index: 3896700 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1396. Min Range: -4.1396
Max Act: 3.7019. Min Act: -0.1700
Data Index: 4951316 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19