Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.5168. Min Act: -0.1700
Data Index: 7520202 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.2981. Min Act: -0.1700
Data Index: 193014 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.2043. Min Act: -0.1700
Data Index: 5247343 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.2043. Min Act: -0.1700
Data Index: 2898952 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.1731. Min Act: -0.1700
Data Index: 7069873 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.1418. Min Act: -0.1700
Data Index: 2402296 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.1106. Min Act: -0.1700
Data Index: 1675152 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.1418. Min Act: -0.1700
Data Index: 407194 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.1106. Min Act: -0.1700
Data Index: 5806516 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.1106. Min Act: -0.1700
Data Index: 8748047 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0793. Min Act: -0.1700
Data Index: 7722337 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0793. Min Act: -0.1700
Data Index: 8790666 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0481. Min Act: -0.1700
Data Index: 3634426 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0481. Min Act: -0.1700
Data Index: 2499224 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0481. Min Act: -0.1700
Data Index: 8288136 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0168. Min Act: -0.1700
Data Index: 3308937 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0168. Min Act: -0.1700
Data Index: 2713403 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0168. Min Act: -0.1700
Data Index: 1177562 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5168. Min Range: -5.5168
Max Act: 5.0168. Min Act: -0.1700
Data Index: 6570685 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5168. Min Range: -5.5168
Max Act: 4.9856. Min Act: -0.1700
Data Index: 7874732 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19