Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5723 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.5500. Min Act: -0.1700
Data Index: 746739 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.5188. Min Act: -0.1700
Data Index: 7541960 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.4250. Min Act: -0.1700
Data Index: 6336989 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.3938. Min Act: -0.1700
Data Index: 6448116 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.2375. Min Act: -0.1700
Data Index: 6092144 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.2375. Min Act: -0.1700
Data Index: 468958 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.1437. Min Act: -0.1700
Data Index: 4369623 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.1437. Min Act: -0.1700
Data Index: 6717772 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.1125. Min Act: -0.1700
Data Index: 7919985 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.0812. Min Act: -0.1700
Data Index: 1039642 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.0500. Min Act: -0.1700
Data Index: 6218617 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.0500. Min Act: -0.1700
Data Index: 6685744 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.0500. Min Act: -0.1700
Data Index: 6112627 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.0500. Min Act: -0.1700
Data Index: 3336362 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5500. Min Range: -4.5500
Max Act: 3.9875. Min Act: -0.1700
Data Index: 7680798 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5500. Min Range: -4.5500
Max Act: 4.0187. Min Act: -0.1700
Data Index: 1579942 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5500. Min Range: -4.5500
Max Act: 3.9562. Min Act: -0.1700
Data Index: 6521625 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5500. Min Range: -4.5500
Max Act: 3.9875. Min Act: -0.1700
Data Index: 452589 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5500. Min Range: -4.5500
Max Act: 3.9875. Min Act: -0.1700
Data Index: 3316178 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5500. Min Range: -4.5500
Max Act: 3.9562. Min Act: -0.1700
Data Index: 2676957 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19