Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5226 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.2693. Min Act: -0.1700
Data Index: 2361783 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.2850. Min Act: -0.1700
Data Index: 1550270 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.2379. Min Act: -0.1700
Data Index: 2976473 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.2222. Min Act: -0.1700
Data Index: 5063031 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1750. Min Act: -0.1700
Data Index: 6243228 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1593. Min Act: -0.1700
Data Index: 3251485 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1435. Min Act: -0.1700
Data Index: 6379015 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1593. Min Act: -0.1700
Data Index: 1875937 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1593. Min Act: -0.1700
Data Index: 7752922 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1593. Min Act: -0.1700
Data Index: 8061955 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1593. Min Act: -0.1700
Data Index: 6677073 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1593. Min Act: -0.1700
Data Index: 1672733 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.1435. Min Act: -0.1700
Data Index: 4077571 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.0962. Min Act: -0.1700
Data Index: 7725653 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.0647. Min Act: -0.1700
Data Index: 158447 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.0647. Min Act: -0.1700
Data Index: 8199999 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.0489. Min Act: -0.1700
Data Index: 4912647 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.0647. Min Act: -0.1700
Data Index: 2319589 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.0647. Min Act: -0.1700
Data Index: 903089 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2850. Min Range: -3.2850
Max Act: 3.0805. Min Act: -0.1700
Data Index: 8537617 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19