Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2373 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6552. Min Act: -0.1700
Data Index: 7496682 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6240. Min Act: -0.1700
Data Index: 240589 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 1118520 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 5166438 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 3034363 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4990. Min Act: -0.1700
Data Index: 5407300 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 1319247 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4990. Min Act: -0.1700
Data Index: 6717560 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4364. Min Act: -0.1700
Data Index: 232527 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4990. Min Act: -0.1700
Data Index: 2688215 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4677. Min Act: -0.1700
Data Index: 8295369 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4052. Min Act: -0.1700
Data Index: 217232 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4364. Min Act: -0.1700
Data Index: 7770630 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4052. Min Act: -0.1700
Data Index: 6189521 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4052. Min Act: -0.1700
Data Index: 6770424 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4364. Min Act: -0.1700
Data Index: 282057 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4052. Min Act: -0.1700
Data Index: 7840543 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4052. Min Act: -0.1700
Data Index: 1798357 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.3739. Min Act: -0.1700
Data Index: 4095931 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4052. Min Act: -0.1700
Data Index: 1700005 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19