Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.4870. Min Act: -0.1700
Data Index: 4966203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.4220. Min Act: -0.1700
Data Index: 706616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.3402. Min Act: -0.1700
Data Index: 2106953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.3238. Min Act: -0.1700
Data Index: 174848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.2909. Min Act: -0.1700
Data Index: 2390838 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.2415. Min Act: -0.1700
Data Index: 4304571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.2249. Min Act: -0.1700
Data Index: 1580449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.2249. Min Act: -0.1700
Data Index: 3397237 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.2083. Min Act: -0.1700
Data Index: 4981760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1917. Min Act: -0.1700
Data Index: 3991708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1917. Min Act: -0.1700
Data Index: 7418480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1917. Min Act: -0.1700
Data Index: 4335193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1917. Min Act: -0.1700
Data Index: 4512603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1917. Min Act: -0.1700
Data Index: 5980847 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1751. Min Act: -0.1700
Data Index: 5351144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1751. Min Act: -0.1700
Data Index: 6031307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1751. Min Act: -0.1700
Data Index: 2071463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1751. Min Act: -0.1700
Data Index: 2223449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1751. Min Act: -0.1699
Data Index: 3028519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4870. Min Range: -2.4870
Max Act: 2.1751. Min Act: -0.1700
Data Index: 1483437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19