Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.2224. Min Act: -0.1700
Data Index: 7876292 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.1599. Min Act: -0.1700
Data Index: 2838366 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.1287. Min Act: -0.1700
Data Index: 2330797 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.1599. Min Act: -0.1700
Data Index: 7142283 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 6763256 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 7797009 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 5357763 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 2621214 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0349. Min Act: -0.1700
Data Index: 6289556 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0662. Min Act: -0.1700
Data Index: 8174675 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0662. Min Act: -0.1700
Data Index: 7452871 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0349. Min Act: -0.1700
Data Index: 758892 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0662. Min Act: -0.1700
Data Index: 3259040 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0662. Min Act: -0.1700
Data Index: 1504212 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0662. Min Act: -0.1700
Data Index: 4093717 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0349. Min Act: -0.1700
Data Index: 1028289 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2224. Min Range: -4.2224
Max Act: 4.0349. Min Act: -0.1700
Data Index: 7742574 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2224. Min Range: -4.2224
Max Act: 3.9724. Min Act: -0.1700
Data Index: 3376850 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2224. Min Range: -4.2224
Max Act: 3.9724. Min Act: -0.1700
Data Index: 1454271 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2224. Min Range: -4.2224
Max Act: 3.9411. Min Act: -0.1700
Data Index: 7566752 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19