Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.9384. Min Act: -0.1700
Data Index: 2331552 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.9384. Min Act: -0.1700
Data Index: 1637119 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8432. Min Act: -0.1700
Data Index: 4905199 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 7447247 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8273. Min Act: -0.1700
Data Index: 983822 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1195685 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7636. Min Act: -0.1700
Data Index: 2132867 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7476. Min Act: -0.1700
Data Index: 6941488 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7636. Min Act: -0.1700
Data Index: 2844889 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7157. Min Act: -0.1700
Data Index: 4727129 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7157. Min Act: -0.1700
Data Index: 2844890 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7157. Min Act: -0.1699
Data Index: 7000715 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6997. Min Act: -0.1700
Data Index: 5689042 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6837. Min Act: -0.1700
Data Index: 5238981 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6837. Min Act: -0.1700
Data Index: 4070573 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6837. Min Act: -0.1700
Data Index: 2062383 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6837. Min Act: -0.1700
Data Index: 4763999 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6516. Min Act: -0.1700
Data Index: 5746835 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6677. Min Act: -0.1700
Data Index: 5247722 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.6677. Min Act: -0.1700
Data Index: 1042044 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19