Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0446. Min Range: -4.0446
Max Act: 4.0446. Min Act: -0.1700
Data Index: 4462511 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0446. Min Range: -4.0446
Max Act: 4.0133. Min Act: -0.1700
Data Index: 8469763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0446. Min Range: -4.0446
Max Act: 4.0133. Min Act: -0.1700
Data Index: 6051540 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0446. Min Range: -4.0446
Max Act: 4.0133. Min Act: -0.1700
Data Index: 6753075 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9821. Min Act: -0.1700
Data Index: 4885894 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9821. Min Act: -0.1700
Data Index: 2200873 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9821. Min Act: -0.1700
Data Index: 158499 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9821. Min Act: -0.1700
Data Index: 2561377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9821. Min Act: -0.1700
Data Index: 1872199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9508. Min Act: -0.1700
Data Index: 2561375 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9195. Min Act: -0.1700
Data Index: 742979 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9508. Min Act: -0.1700
Data Index: 2522819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9508. Min Act: -0.1700
Data Index: 8552064 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.8883. Min Act: -0.1700
Data Index: 5756176 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9195. Min Act: -0.1700
Data Index: 5223075 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9195. Min Act: -0.1700
Data Index: 2391917 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9195. Min Act: -0.1700
Data Index: 6102684 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9195. Min Act: -0.1700
Data Index: 6362320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.9195. Min Act: -0.1700
Data Index: 2870988 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0446. Min Range: -4.0446
Max Act: 3.8883. Min Act: -0.1700
Data Index: 2870986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19