Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.7966. Min Act: -0.1700
Data Index: 3252040 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.7654. Min Act: -0.1700
Data Index: 7791438 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.7341. Min Act: -0.1700
Data Index: 1238473 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.7029. Min Act: -0.1700
Data Index: 1750710 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.7029. Min Act: -0.1700
Data Index: 8221894 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.7029. Min Act: -0.1700
Data Index: 4759458 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6404. Min Act: -0.1700
Data Index: 7384916 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6716. Min Act: -0.1700
Data Index: 70898 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6716. Min Act: -0.1700
Data Index: 5715237 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6404. Min Act: -0.1700
Data Index: 8572064 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6404. Min Act: -0.1700
Data Index: 1667437 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6404. Min Act: -0.1700
Data Index: 8754281 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6404. Min Act: -0.1700
Data Index: 1321918 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6091. Min Act: -0.1700
Data Index: 3870572 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6091. Min Act: -0.1700
Data Index: 1130083 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6404. Min Act: -0.1700
Data Index: 60629 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6091. Min Act: -0.1700
Data Index: 850521 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6091. Min Act: -0.1700
Data Index: 1940256 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6091. Min Act: -0.1700
Data Index: 6072275 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7966. Min Range: -5.7966
Max Act: 5.6091. Min Act: -0.1700
Data Index: 6402899 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19