Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 636 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.3595. Min Act: -0.1700
Data Index: 7724685 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2967. Min Act: -0.1700
Data Index: 1543508 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2967. Min Act: -0.1700
Data Index: 1426098 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2653. Min Act: -0.1700
Data Index: 779174 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 2444873 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 168027 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 2756926 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 95429 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2025. Min Act: -0.1700
Data Index: 8589086 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 7139641 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 72237 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1773368 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1746457 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1665977 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 5838067 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2339. Min Act: -0.1700
Data Index: 4463513 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2025. Min Act: -0.1700
Data Index: 2185109 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.1710. Min Act: -0.1700
Data Index: 25286 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.2025. Min Act: -0.1700
Data Index: 3605565 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3595. Min Range: -3.3595
Max Act: 3.1710. Min Act: -0.1700
Data Index: 3705085 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19