Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.9369. Min Act: -0.1700
Data Index: 3665686 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.7807. Min Act: -0.1700
Data Index: 7859997 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.7182. Min Act: -0.1700
Data Index: 266526 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.6869. Min Act: -0.1700
Data Index: 464325 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.7182. Min Act: -0.1700
Data Index: 246978 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.6557. Min Act: -0.1700
Data Index: 4017374 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.6557. Min Act: -0.1700
Data Index: 2262031 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.6244. Min Act: -0.1700
Data Index: 3710255 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.6557. Min Act: -0.1700
Data Index: 4785544 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.6244. Min Act: -0.1700
Data Index: 7986488 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.5932. Min Act: -0.1700
Data Index: 1177796 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.5932. Min Act: -0.1700
Data Index: 6033968 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.6244. Min Act: -0.1700
Data Index: 247459 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.5619. Min Act: -0.1700
Data Index: 7470615 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.4994. Min Act: -0.1700
Data Index: 1299204 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.4682. Min Act: -0.1700
Data Index: 947007 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.4994. Min Act: -0.1700
Data Index: 3416594 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.4369. Min Act: -0.1700
Data Index: 336190 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.4682. Min Act: -0.1700
Data Index: 3665687 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9369. Min Range: -7.9369
Max Act: 7.4057. Min Act: -0.1700
Data Index: 612049 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19