Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 344 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.3746. Min Act: -0.1700
Data Index: 1673486 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.3434. Min Act: -0.1700
Data Index: 941060 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.2496. Min Act: -0.1700
Data Index: 8474128 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.2184. Min Act: -0.1700
Data Index: 6576103 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1871. Min Act: -0.1700
Data Index: 698447 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1559. Min Act: -0.1700
Data Index: 4707000 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1871. Min Act: -0.1700
Data Index: 2469561 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1246. Min Act: -0.1700
Data Index: 8360157 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.0934. Min Act: -0.1700
Data Index: 19933 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1246. Min Act: -0.1700
Data Index: 5150956 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1246. Min Act: -0.1700
Data Index: 3363038 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1246. Min Act: -0.1700
Data Index: 5527383 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.0934. Min Act: -0.1700
Data Index: 925255 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.0621. Min Act: -0.1700
Data Index: 3363032 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.0309. Min Act: -0.1700
Data Index: 8632125 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.0309. Min Act: -0.1700
Data Index: 7148202 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.0309. Min Act: -0.1700
Data Index: 4528127 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.0309. Min Act: -0.1700
Data Index: 818894 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9996. Min Act: -0.1700
Data Index: 8110624 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9684. Min Act: -0.1700
Data Index: 4028302 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19