Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.6232. Min Act: -0.1700
Data Index: 423432 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.5920. Min Act: -0.1700
Data Index: 6544827 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.5295. Min Act: -0.1700
Data Index: 367475 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.5295. Min Act: -0.1700
Data Index: 1265563 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.5295. Min Act: -0.1700
Data Index: 4543068 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.4982. Min Act: -0.1700
Data Index: 5984678 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.4670. Min Act: -0.1700
Data Index: 5709027 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.4670. Min Act: -0.1700
Data Index: 16923 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.4670. Min Act: -0.1700
Data Index: 8431883 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.4357. Min Act: -0.1700
Data Index: 7857434 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.4045. Min Act: -0.1700
Data Index: 5298747 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.3732. Min Act: -0.1700
Data Index: 4543067 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.3732. Min Act: -0.1700
Data Index: 6354870 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.2795. Min Act: -0.1700
Data Index: 5007710 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.2482. Min Act: -0.1700
Data Index: 2615406 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.2482. Min Act: -0.1700
Data Index: 6125279 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.2482. Min Act: -0.1700
Data Index: 2049674 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.2170. Min Act: -0.1700
Data Index: 2415405 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.2482. Min Act: -0.1700
Data Index: 4448480 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6232. Min Range: -5.6232
Max Act: 5.2482. Min Act: -0.1700
Data Index: 1583918 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19