Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 846 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.4419. Min Act: -0.1700
Data Index: 8437210 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.3481. Min Act: -0.1700
Data Index: 7340010 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.3481. Min Act: -0.1700
Data Index: 6307206 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.3169. Min Act: -0.1700
Data Index: 7910405 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2544. Min Act: -0.1700
Data Index: 6328615 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2544. Min Act: -0.1700
Data Index: 427003 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2544. Min Act: -0.1700
Data Index: 8130625 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2544. Min Act: -0.1700
Data Index: 8726516 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2544. Min Act: -0.1700
Data Index: 7226425 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2231. Min Act: -0.1700
Data Index: 477690 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2231. Min Act: -0.1700
Data Index: 4436480 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.2231. Min Act: -0.1700
Data Index: 5910567 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.1606. Min Act: -0.1700
Data Index: 7178248 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.1294. Min Act: -0.1700
Data Index: 6435933 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.1294. Min Act: -0.1700
Data Index: 1444085 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.0669. Min Act: -0.1700
Data Index: 5541375 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.0981. Min Act: -0.1700
Data Index: 158819 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.1294. Min Act: -0.1700
Data Index: 3175219 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.1294. Min Act: -0.1700
Data Index: 970537 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4419. Min Range: -5.4419
Max Act: 5.1294. Min Act: -0.1700
Data Index: 2864025 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19