Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5217 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.1644. Min Act: -0.1700
Data Index: 2413576 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.1019. Min Act: -0.1700
Data Index: 6307261 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0706. Min Act: -0.1700
Data Index: 4726342 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0394. Min Act: -0.1700
Data Index: 5053058 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0081. Min Act: -0.1700
Data Index: 8737722 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0394. Min Act: -0.1700
Data Index: 4369752 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0706. Min Act: -0.1700
Data Index: 7523288 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0081. Min Act: -0.1700
Data Index: 7720466 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0081. Min Act: -0.1700
Data Index: 7671102 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0081. Min Act: -0.1700
Data Index: 6522084 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9769. Min Act: -0.1700
Data Index: 2219167 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9769. Min Act: -0.1700
Data Index: 8776184 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1644. Min Range: -5.1644
Max Act: 5.0081. Min Act: -0.1700
Data Index: 2608860 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9144. Min Act: -0.1700
Data Index: 5832194 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9456. Min Act: -0.1700
Data Index: 25710 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9456. Min Act: -0.1700
Data Index: 3223920 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9456. Min Act: -0.1700
Data Index: 6439924 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9456. Min Act: -0.1700
Data Index: 4920852 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9144. Min Act: -0.1700
Data Index: 6674516 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1644. Min Range: -5.1644
Max Act: 4.9456. Min Act: -0.1700
Data Index: 6928908 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19