Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0470. Min Range: -5.0470
Max Act: 5.0470. Min Act: -0.1700
Data Index: 1452468 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0470. Min Range: -5.0470
Max Act: 5.0470. Min Act: -0.1700
Data Index: 1452476 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0470. Min Range: -5.0470
Max Act: 5.0157. Min Act: -0.1700
Data Index: 561421 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0470. Min Range: -5.0470
Max Act: 5.0157. Min Act: -0.1700
Data Index: 5686834 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9532. Min Act: -0.1700
Data Index: 3721553 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9532. Min Act: -0.1700
Data Index: 3618066 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9845. Min Act: -0.1700
Data Index: 1452477 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9845. Min Act: -0.1700
Data Index: 1452464 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9532. Min Act: -0.1700
Data Index: 6893585 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9220. Min Act: -0.1700
Data Index: 7566087 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9532. Min Act: -0.1700
Data Index: 900231 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9220. Min Act: -0.1700
Data Index: 7020093 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9220. Min Act: -0.1700
Data Index: 5162953 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.9220. Min Act: -0.1700
Data Index: 4814501 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.8907. Min Act: -0.1700
Data Index: 3494356 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.8907. Min Act: -0.1700
Data Index: 62711 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.8907. Min Act: -0.1700
Data Index: 8731130 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.8907. Min Act: -0.1700
Data Index: 7676579 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.8595. Min Act: -0.1700
Data Index: 5639341 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0470. Min Range: -5.0470
Max Act: 4.8595. Min Act: -0.1700
Data Index: 1452470 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19