Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 119 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4357. Min Act: -0.1700
Data Index: 1643432 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2169. Min Act: -0.1700
Data Index: 8087877 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1232. Min Act: -0.1700
Data Index: 2455388 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.0607. Min Act: -0.1700
Data Index: 6871356 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.0294. Min Act: -0.1700
Data Index: 5278342 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.0294. Min Act: -0.1700
Data Index: 6078725 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.9982. Min Act: -0.1700
Data Index: 1309823 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.9982. Min Act: -0.1700
Data Index: 879320 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.9669. Min Act: -0.1700
Data Index: 8447149 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.9669. Min Act: -0.1700
Data Index: 2106301 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.9357. Min Act: -0.1700
Data Index: 7491132 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.9044. Min Act: -0.1700
Data Index: 3804939 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 3370517 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8732. Min Act: -0.1700
Data Index: 2330841 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 8259112 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 4647653 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8732. Min Act: -0.1700
Data Index: 3370958 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 665222 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 118116 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4357. Min Range: -5.4357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 8416817 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19