Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2216 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.5241. Min Range: -10.5241
Max Act: 10.5241. Min Act: -0.1700
Data Index: 7480118 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5241. Min Range: -10.5241
Max Act: 10.1491. Min Act: -0.1700
Data Index: 7190571 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.8991. Min Act: -0.1700
Data Index: 1160242 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.7116. Min Act: -0.1700
Data Index: 5173333 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.7741. Min Act: -0.1700
Data Index: 5173331 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.7116. Min Act: -0.1700
Data Index: 4477746 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5866. Min Act: -0.1700
Data Index: 3542377 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.6491. Min Act: -0.1700
Data Index: 4512927 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5866. Min Act: -0.1700
Data Index: 4477732 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.4616. Min Act: -0.1700
Data Index: 3542383 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5241. Min Act: -0.1700
Data Index: 1587779 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5241. Min Act: -0.1700
Data Index: 7828372 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3366. Min Act: -0.1700
Data Index: 4855722 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.4616. Min Act: -0.1700
Data Index: 4959866 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5241. Min Act: -0.1700
Data Index: 4181201 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.4616. Min Act: -0.1700
Data Index: 1913107 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.4616. Min Act: -0.1700
Data Index: 7347388 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3991. Min Act: -0.1700
Data Index: 1364971 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3991. Min Act: -0.1700
Data Index: 1160244 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3366. Min Act: -0.1700
Data Index: 4302251 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19