Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.8339. Min Act: -0.1700
Data Index: 5603815 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.7557. Min Act: -0.1700
Data Index: 976458 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.7401. Min Act: -0.1700
Data Index: 1615136 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.7245. Min Act: -0.1700
Data Index: 4581089 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.6932. Min Act: -0.1700
Data Index: 8510623 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.6306. Min Act: -0.1700
Data Index: 2265707 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.6462. Min Act: -0.1700
Data Index: 7685101 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5993. Min Act: -0.1700
Data Index: 723258 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.6149. Min Act: -0.1700
Data Index: 1358047 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5523. Min Act: -0.1700
Data Index: 8701595 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5680. Min Act: -0.1700
Data Index: 1396207 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5523. Min Act: -0.1700
Data Index: 4718784 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5523. Min Act: -0.1700
Data Index: 8226618 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5523. Min Act: -0.1700
Data Index: 5135825 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5210. Min Act: -0.1700
Data Index: 1446994 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5210. Min Act: -0.1700
Data Index: 4648419 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5210. Min Act: -0.1700
Data Index: 4833948 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.4897. Min Act: -0.1700
Data Index: 2940288 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5210. Min Act: -0.1700
Data Index: 2052716 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8339. Min Range: -3.8339
Max Act: 3.5053. Min Act: -0.1700
Data Index: 3035188 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19