Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.6237. Min Act: -0.1700
Data Index: 4746341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.6237. Min Act: -0.1698
Data Index: 4070199 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.6550. Min Act: -0.1700
Data Index: 8359840 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5925. Min Act: -0.1700
Data Index: 2127840 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5612. Min Act: -0.1699
Data Index: 3195446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 5296849 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5612. Min Act: -0.1700
Data Index: 3355406 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 2791198 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 3839260 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 1438797 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.4987. Min Act: -0.1700
Data Index: 1002468 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 4972066 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 8373326 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 6046325 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.5300. Min Act: -0.1700
Data Index: 1231594 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.4987. Min Act: -0.1700
Data Index: 2576900 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.4987. Min Act: -0.1700
Data Index: 4896541 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.4675. Min Act: -0.1700
Data Index: 4760252 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.4987. Min Act: -0.1700
Data Index: 2402632 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6550. Min Range: -4.6550
Max Act: 4.4987. Min Act: -0.1695
Data Index: 2362725 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19