Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.7359. Min Act: -0.1700
Data Index: 8691554 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.6734. Min Act: -0.1700
Data Index: 4463103 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.6734. Min Act: -0.1700
Data Index: 4067642 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.4859. Min Act: -0.1700
Data Index: 5157264 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.4234. Min Act: -0.1700
Data Index: 3125013 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.4234. Min Act: -0.1700
Data Index: 6272052 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.3609. Min Act: -0.1700
Data Index: 4391854 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2984. Min Act: -0.1700
Data Index: 2600811 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2671. Min Act: -0.1700
Data Index: 3141159 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2671. Min Act: -0.1700
Data Index: 3071548 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2671. Min Act: -0.1700
Data Index: 637262 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2359. Min Act: -0.1700
Data Index: 3155243 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2359. Min Act: -0.1700
Data Index: 7859788 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2046. Min Act: -0.1700
Data Index: 4395750 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2359. Min Act: -0.1700
Data Index: 6688051 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2046. Min Act: -0.1700
Data Index: 1713621 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2046. Min Act: -0.1700
Data Index: 2031614 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2046. Min Act: -0.1700
Data Index: 5338678 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2046. Min Act: -0.1700
Data Index: 8608789 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7359. Min Range: -6.7359
Max Act: 6.2046. Min Act: -0.1700
Data Index: 314586 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19