Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 255 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0427. Min Range: -11.0427
Max Act: 11.0427. Min Act: -0.1700
Data Index: 1532781 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.9802. Min Act: -0.1700
Data Index: 4848908 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.8552. Min Act: -0.1700
Data Index: 1393756 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.8552. Min Act: -0.1700
Data Index: 2095123 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.7302. Min Act: -0.1700
Data Index: 5592784 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.6677. Min Act: -0.1700
Data Index: 3920119 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.6677. Min Act: -0.1700
Data Index: 8404567 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.6677. Min Act: -0.1700
Data Index: 5585718 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.7302. Min Act: -0.1700
Data Index: 1891861 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.6677. Min Act: -0.1700
Data Index: 5681921 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.6052. Min Act: -0.1700
Data Index: 3706549 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.6052. Min Act: -0.1700
Data Index: 4274713 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.5427. Min Act: -0.1700
Data Index: 2060465 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.5427. Min Act: -0.1700
Data Index: 3425710 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.5427. Min Act: -0.1700
Data Index: 4055816 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.5427. Min Act: -0.1700
Data Index: 472428 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.4802. Min Act: -0.1700
Data Index: 8152298 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.4802. Min Act: -0.1700
Data Index: 2091116 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.4802. Min Act: -0.1700
Data Index: 4659809 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0427. Min Range: -11.0427
Max Act: 10.4177. Min Act: -0.1700
Data Index: 4314638 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19