Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.4439. Min Act: -0.1700
Data Index: 8029131 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.4127. Min Act: -0.1700
Data Index: 5259994 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.3502. Min Act: -0.1700
Data Index: 7204721 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.3189. Min Act: -0.1700
Data Index: 3493521 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.2564. Min Act: -0.1700
Data Index: 8180485 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1939. Min Act: -0.1700
Data Index: 2450392 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1939. Min Act: -0.1700
Data Index: 2200610 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1627. Min Act: -0.1700
Data Index: 5106051 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1939. Min Act: -0.1700
Data Index: 6222489 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1939. Min Act: -0.1700
Data Index: 3556049 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1627. Min Act: -0.1700
Data Index: 3080158 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1627. Min Act: -0.1700
Data Index: 5972034 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1314. Min Act: -0.1700
Data Index: 6346741 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1314. Min Act: -0.1700
Data Index: 7990691 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1002. Min Act: -0.1700
Data Index: 4311619 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1314. Min Act: -0.1700
Data Index: 6765048 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1002. Min Act: -0.1700
Data Index: 5878972 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1314. Min Act: -0.1700
Data Index: 7542465 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1314. Min Act: -0.1700
Data Index: 7086001 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4439. Min Range: -4.4439
Max Act: 4.1627. Min Act: -0.1700
Data Index: 7354301 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19