Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1842 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.5052. Min Act: -0.1700
Data Index: 3760577 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.5052. Min Act: -0.1700
Data Index: 1540525 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.4402. Min Act: -0.1700
Data Index: 8566667 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.4239. Min Act: -0.1700
Data Index: 7700542 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3750. Min Act: -0.1700
Data Index: 2970450 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3913. Min Act: -0.1700
Data Index: 2869522 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3750. Min Act: -0.1700
Data Index: 1724947 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3750. Min Act: -0.1700
Data Index: 5939247 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3586. Min Act: -0.1700
Data Index: 8348378 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3586. Min Act: -0.1700
Data Index: 1114390 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3422. Min Act: -0.1700
Data Index: 470775 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3422. Min Act: -0.1700
Data Index: 2940206 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3258. Min Act: -0.1700
Data Index: 4335978 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3422. Min Act: -0.1700
Data Index: 6687052 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3258. Min Act: -0.1700
Data Index: 49462 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3094. Min Act: -0.1698
Data Index: 2199326 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3094. Min Act: -0.1700
Data Index: 3004911 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.3094. Min Act: -0.1700
Data Index: 7427518 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.2929. Min Act: -0.1700
Data Index: 4435519 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5052. Min Range: -2.5052
Max Act: 2.2929. Min Act: -0.1700
Data Index: 4422696 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19