Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.9087. Min Act: -0.1700
Data Index: 715364 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.7837. Min Act: -0.1700
Data Index: 2423714 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.5337. Min Act: -0.1700
Data Index: 4407114 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.5337. Min Act: -0.1700
Data Index: 2766026 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.5024. Min Act: -0.1700
Data Index: 7751100 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.4399. Min Act: -0.1700
Data Index: 5565808 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.3774. Min Act: -0.1700
Data Index: 6257882 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.3774. Min Act: -0.1700
Data Index: 5129748 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.2524. Min Act: -0.1700
Data Index: 1184972 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 7586896 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.1899. Min Act: -0.1700
Data Index: 895530 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 4645831 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 2052259 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 1883415 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 988042 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.1899. Min Act: -0.1700
Data Index: 5530321 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.1899. Min Act: -0.1700
Data Index: 1264523 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.1899. Min Act: -0.1700
Data Index: 719690 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 6263398 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9087. Min Range: -5.9087
Max Act: 5.1899. Min Act: -0.1700
Data Index: 7550645 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19