Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.5658. Min Act: -0.1700
Data Index: 7716651 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.5033. Min Act: -0.1700
Data Index: 1847255 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.5345. Min Act: -0.1700
Data Index: 4630754 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.3470. Min Act: -0.1700
Data Index: 5765782 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2845. Min Act: -0.1700
Data Index: 5020220 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2845. Min Act: -0.1700
Data Index: 225504 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2845. Min Act: -0.1700
Data Index: 4441252 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2220. Min Act: -0.1700
Data Index: 6443700 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2533. Min Act: -0.1700
Data Index: 598177 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2533. Min Act: -0.1700
Data Index: 4914775 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2533. Min Act: -0.1700
Data Index: 3101898 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2220. Min Act: -0.1700
Data Index: 4670496 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2220. Min Act: -0.1700
Data Index: 3590936 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.1908. Min Act: -0.1700
Data Index: 677895 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.2220. Min Act: -0.1700
Data Index: 8616756 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.1908. Min Act: -0.1700
Data Index: 2244075 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.1908. Min Act: -0.1700
Data Index: 3515600 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.1595. Min Act: -0.1700
Data Index: 3990175 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.1595. Min Act: -0.1700
Data Index: 5183291 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5658. Min Range: -6.5658
Max Act: 6.1595. Min Act: -0.1700
Data Index: 5276975 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19