Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2442. Min Range: -8.2442
Max Act: 8.2442. Min Act: -0.1700
Data Index: 2917798 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.7755. Min Act: -0.1700
Data Index: 1746312 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.6817. Min Act: -0.1700
Data Index: 6417150 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.5567. Min Act: -0.1700
Data Index: 5450939 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.4942. Min Act: -0.1700
Data Index: 4140703 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.5255. Min Act: -0.1700
Data Index: 2705795 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.4317. Min Act: -0.1700
Data Index: 8739532 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.3692. Min Act: -0.1700
Data Index: 142097 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.3692. Min Act: -0.1700
Data Index: 7613839 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.3380. Min Act: -0.1700
Data Index: 4715744 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.3380. Min Act: -0.1700
Data Index: 6658343 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.3067. Min Act: -0.1700
Data Index: 8109642 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.3067. Min Act: -0.1700
Data Index: 4997863 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.2442. Min Act: -0.1700
Data Index: 6275241 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.2442. Min Act: -0.1700
Data Index: 2785385 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.2130. Min Act: -0.1700
Data Index: 836760 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.2130. Min Act: -0.1700
Data Index: 1756477 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.2130. Min Act: -0.1700
Data Index: 7850840 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.1817. Min Act: -0.1700
Data Index: 1427360 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2442. Min Range: -8.2442
Max Act: 7.1505. Min Act: -0.1700
Data Index: 3072142 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19