Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.5577. Min Act: -0.1700
Data Index: 7614831 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.4014. Min Act: -0.1700
Data Index: 5050350 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.2764. Min Act: -0.1700
Data Index: 7449453 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.2139. Min Act: -0.1700
Data Index: 8828741 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.1827. Min Act: -0.1700
Data Index: 2356202 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.1827. Min Act: -0.1700
Data Index: 2616984 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.0577. Min Act: -0.1700
Data Index: 1578810 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.0577. Min Act: -0.1700
Data Index: 5595414 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.0264. Min Act: -0.1700
Data Index: 8755340 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.0264. Min Act: -0.1700
Data Index: 6092600 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.9952. Min Act: -0.1700
Data Index: 6480327 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.9952. Min Act: -0.1700
Data Index: 7996990 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5577. Min Range: -6.5577
Max Act: 6.0264. Min Act: -0.1700
Data Index: 498460 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.9952. Min Act: -0.1700
Data Index: 8061527 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.9952. Min Act: -0.1700
Data Index: 3487144 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.9327. Min Act: -0.1700
Data Index: 214452 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.9327. Min Act: -0.1700
Data Index: 2287131 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.8702. Min Act: -0.1700
Data Index: 4893545 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.9014. Min Act: -0.1700
Data Index: 5662611 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5577. Min Range: -6.5577
Max Act: 5.8702. Min Act: -0.1700
Data Index: 2811348 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19