Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.7691. Min Act: -0.1700
Data Index: 8382017 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.7222. Min Act: -0.1700
Data Index: 5899711 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.7222. Min Act: -0.1700
Data Index: 4701035 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.6440. Min Act: -0.1700
Data Index: 6479124 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.6440. Min Act: -0.1700
Data Index: 8251828 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.6440. Min Act: -0.1700
Data Index: 418123 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.6596. Min Act: -0.1700
Data Index: 4162573 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.6440. Min Act: -0.1700
Data Index: 3168467 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5970. Min Act: -0.1700
Data Index: 6218020 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5814. Min Act: -0.1700
Data Index: 7533935 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.6127. Min Act: -0.1700
Data Index: 693533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5814. Min Act: -0.1700
Data Index: 7010495 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5657. Min Act: -0.1700
Data Index: 6678082 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5814. Min Act: -0.1700
Data Index: 3763930 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5657. Min Act: -0.1700
Data Index: 1958816 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5657. Min Act: -0.1700
Data Index: 7718337 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5344. Min Act: -0.1700
Data Index: 6186314 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5344. Min Act: -0.1700
Data Index: 7584866 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5344. Min Act: -0.1700
Data Index: 1896140 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7691. Min Range: -3.7691
Max Act: 3.5344. Min Act: -0.1700
Data Index: 2734780 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19