Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.9750. Min Act: -0.1700
Data Index: 6644884 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.9438. Min Act: -0.1700
Data Index: 5775406 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.8500. Min Act: -0.1700
Data Index: 4815236 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7875. Min Act: -0.1700
Data Index: 2122935 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.8188. Min Act: -0.1700
Data Index: 1094417 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7250. Min Act: -0.1700
Data Index: 7938405 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 2044351 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7250. Min Act: -0.1700
Data Index: 6457727 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7250. Min Act: -0.1700
Data Index: 2075158 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 5350253 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 2089273 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 1150575 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 7492165 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 8740885 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6625. Min Act: -0.1700
Data Index: 2469921 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6625. Min Act: -0.1700
Data Index: 5831460 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6625. Min Act: -0.1700
Data Index: 6655056 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6625. Min Act: -0.1700
Data Index: 8078896 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6313. Min Act: -0.1700
Data Index: 2092824 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6313. Min Act: -0.1700
Data Index: 1959261 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19