Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6108 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1097. Min Range: -4.1097
Max Act: 4.1097. Min Act: -0.1700
Data Index: 1114819 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1097. Min Range: -4.1097
Max Act: 4.0472. Min Act: -0.1700
Data Index: 6544927 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1097. Min Range: -4.1097
Max Act: 4.0785. Min Act: -0.1700
Data Index: 3551827 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1097. Min Range: -4.1097
Max Act: 4.0003. Min Act: -0.1700
Data Index: 8362177 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.9847. Min Act: -0.1700
Data Index: 3489814 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.9534. Min Act: -0.1700
Data Index: 7099628 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.9691. Min Act: -0.1700
Data Index: 2368586 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.9534. Min Act: -0.1700
Data Index: 785540 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.9222. Min Act: -0.1700
Data Index: 4472632 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.9222. Min Act: -0.1700
Data Index: 1178769 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.9065. Min Act: -0.1700
Data Index: 4266058 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.8284. Min Act: -0.1700
Data Index: 6454024 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.8284. Min Act: -0.1700
Data Index: 1914657 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.8127. Min Act: -0.1700
Data Index: 6082428 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.8127. Min Act: -0.1700
Data Index: 3738696 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.8127. Min Act: -0.1700
Data Index: 8588622 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.7971. Min Act: -0.1700
Data Index: 8828680 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.7971. Min Act: -0.1700
Data Index: 897416 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.7814. Min Act: -0.1700
Data Index: 8446394 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1097. Min Range: -4.1097
Max Act: 3.7814. Min Act: -0.1700
Data Index: 2730956 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19