Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.8215. Min Act: -0.1700
Data Index: 2493516 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.8215. Min Act: -0.1700
Data Index: 8385205 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.6965. Min Act: -0.1700
Data Index: 1736635 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.6653. Min Act: -0.1700
Data Index: 8128581 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.6653. Min Act: -0.1700
Data Index: 7056160 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.6340. Min Act: -0.1700
Data Index: 7056163 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.5403. Min Act: -0.1700
Data Index: 7084417 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.5403. Min Act: -0.1700
Data Index: 5020984 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4778. Min Act: -0.1700
Data Index: 6005595 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4778. Min Act: -0.1700
Data Index: 2635186 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4778. Min Act: -0.1700
Data Index: 6497385 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4465. Min Act: -0.1700
Data Index: 6536996 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4778. Min Act: -0.1700
Data Index: 6300944 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.3840. Min Act: -0.1700
Data Index: 7659865 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4465. Min Act: -0.1700
Data Index: 6795290 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4153. Min Act: -0.1700
Data Index: 5491925 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.4153. Min Act: -0.1700
Data Index: 1595819 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.3840. Min Act: -0.1700
Data Index: 464989 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.3840. Min Act: -0.1700
Data Index: 7659575 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8215. Min Range: -5.8215
Max Act: 5.3840. Min Act: -0.1700
Data Index: 4625909 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19