Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.8268. Min Act: -0.1700
Data Index: 1221972 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.5768. Min Act: -0.1700
Data Index: 4429197 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.5768. Min Act: -0.1700
Data Index: 2377521 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.3893. Min Act: -0.1700
Data Index: 4475469 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.3268. Min Act: -0.1700
Data Index: 3295799 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.2643. Min Act: -0.1700
Data Index: 2829722 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.2018. Min Act: -0.1700
Data Index: 8300570 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.2018. Min Act: -0.1700
Data Index: 2829728 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 118184 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 6936221 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 3450604 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 6033509 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 2780202 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.0768. Min Act: -0.1700
Data Index: 3816325 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 4594421 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.0768. Min Act: -0.1700
Data Index: 4429212 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.0768. Min Act: -0.1700
Data Index: 4083546 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.0456. Min Act: -0.1700
Data Index: 6787204 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.0768. Min Act: -0.1700
Data Index: 4083543 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8268. Min Range: -7.8268
Max Act: 7.0456. Min Act: -0.1700
Data Index: 6038960 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19