Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4144 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.3596. Min Act: -0.1700
Data Index: 8712476 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.3283. Min Act: -0.1700
Data Index: 7099595 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.3283. Min Act: -0.1700
Data Index: 335322 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.2658. Min Act: -0.1700
Data Index: 2129666 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.2971. Min Act: -0.1700
Data Index: 3442355 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 6812731 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 1723041 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1408. Min Act: -0.1700
Data Index: 5265136 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1408. Min Act: -0.1700
Data Index: 1800319 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 3498964 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 5027114 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 2159037 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 1974675 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 8371863 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 7357425 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 1267928 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 7123995 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.0471. Min Act: -0.1700
Data Index: 1250213 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.0783. Min Act: -0.1700
Data Index: 3941823 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3596. Min Range: -5.3596
Max Act: 5.1096. Min Act: -0.1700
Data Index: 4134810 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19