Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1677. Min Range: -5.1677
Max Act: 5.1677. Min Act: -0.1700
Data Index: 4536685 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1677. Min Range: -5.1677
Max Act: 5.0427. Min Act: -0.1700
Data Index: 7242801 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1677. Min Range: -5.1677
Max Act: 5.0114. Min Act: -0.1700
Data Index: 5709196 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.9177. Min Act: -0.1700
Data Index: 1217303 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8552. Min Act: -0.1700
Data Index: 3633984 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.9177. Min Act: -0.1700
Data Index: 7487602 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8864. Min Act: -0.1700
Data Index: 630507 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8552. Min Act: -0.1700
Data Index: 2053494 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.9489. Min Act: -0.1700
Data Index: 6849711 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8239. Min Act: -0.1700
Data Index: 3680590 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8552. Min Act: -0.1700
Data Index: 1647474 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8239. Min Act: -0.1700
Data Index: 7521885 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8239. Min Act: -0.1700
Data Index: 4958207 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8552. Min Act: -0.1700
Data Index: 1086721 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.7927. Min Act: -0.1700
Data Index: 5933925 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8239. Min Act: -0.1700
Data Index: 4474579 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.7927. Min Act: -0.1700
Data Index: 6263817 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.8239. Min Act: -0.1700
Data Index: 1283651 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1567860 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1677. Min Range: -5.1677
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1424382 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19