Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.9806. Min Act: -0.1700
Data Index: 5366395 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.9806. Min Act: -0.1700
Data Index: 6090342 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.9181. Min Act: -0.1700
Data Index: 7210565 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.8243. Min Act: -0.1700
Data Index: 4487649 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.8087. Min Act: -0.1700
Data Index: 850244 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.8243. Min Act: -0.1700
Data Index: 8783937 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.8087. Min Act: -0.1700
Data Index: 6981682 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7930. Min Act: -0.1700
Data Index: 2864006 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.8087. Min Act: -0.1700
Data Index: 5938977 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7774. Min Act: -0.1700
Data Index: 4886983 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7774. Min Act: -0.1700
Data Index: 7768987 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7774. Min Act: -0.1700
Data Index: 7455792 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7930. Min Act: -0.1700
Data Index: 4205306 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7461. Min Act: -0.1700
Data Index: 8111746 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7461. Min Act: -0.1700
Data Index: 1402293 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7461. Min Act: -0.1700
Data Index: 517964 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7305. Min Act: -0.1700
Data Index: 6094129 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7305. Min Act: -0.1700
Data Index: 1145672 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7148. Min Act: -0.1700
Data Index: 1161683 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9806. Min Range: -3.9806
Max Act: 3.7305. Min Act: -0.1700
Data Index: 2971742 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19