Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1476. Min Act: -0.1700
Data Index: 5232532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1319. Min Act: -0.1700
Data Index: 6775867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1319. Min Act: -0.1700
Data Index: 8186209 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1319. Min Act: -0.1700
Data Index: 5190482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1161. Min Act: -0.1700
Data Index: 5478269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1161. Min Act: -0.1700
Data Index: 6756716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1161. Min Act: -0.1700
Data Index: 5811321 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1161. Min Act: -0.1700
Data Index: 222749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1161. Min Act: -0.1700
Data Index: 2557926 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1161. Min Act: -0.1700
Data Index: 171265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1161. Min Act: -0.1700
Data Index: 2706485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1003. Min Act: -0.1700
Data Index: 6171268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1003. Min Act: -0.1700
Data Index: 6555528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1003. Min Act: -0.1700
Data Index: 6448616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.0846. Min Act: -0.1700
Data Index: 2529251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1003. Min Act: -0.1700
Data Index: 8654864 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.1003. Min Act: -0.1700
Data Index: 212934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.0846. Min Act: -0.1700
Data Index: 1189154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.0846. Min Act: -0.1700
Data Index: 3273880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1476. Min Range: -3.1476
Max Act: 3.0846. Min Act: -0.1700
Data Index: 4378930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19