Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2263 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.6968. Min Act: -0.1700
Data Index: 4421620 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.6029. Min Act: -0.1700
Data Index: 5639730 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.5873. Min Act: -0.1700
Data Index: 5774342 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.5716. Min Act: -0.1700
Data Index: 2620137 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.5716. Min Act: -0.1700
Data Index: 4611458 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.5090. Min Act: -0.1700
Data Index: 6050095 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.4777. Min Act: -0.1700
Data Index: 2218640 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.4620. Min Act: -0.1700
Data Index: 1353445 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.4307. Min Act: -0.1700
Data Index: 1983621 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.4463. Min Act: -0.1700
Data Index: 6311973 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.4150. Min Act: -0.1700
Data Index: 8144744 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.4150. Min Act: -0.1700
Data Index: 932442 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3993. Min Act: -0.1700
Data Index: 8598815 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3836. Min Act: -0.1700
Data Index: 1618597 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3993. Min Act: -0.1700
Data Index: 7859930 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3836. Min Act: -0.1700
Data Index: 1466167 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3836. Min Act: -0.1700
Data Index: 115210 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3680. Min Act: -0.1700
Data Index: 1327187 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3523. Min Act: -0.1700
Data Index: 6604310 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6968. Min Range: -3.6968
Max Act: 3.3680. Min Act: -0.1700
Data Index: 6982885 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19