Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.1450. Min Act: -0.1700
Data Index: 5716636 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0949. Min Act: -0.1700
Data Index: 5716640 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0949. Min Act: -0.1700
Data Index: 7318016 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0445. Min Act: -0.1700
Data Index: 5843621 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0445. Min Act: -0.1700
Data Index: 5843617 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0445. Min Act: -0.1700
Data Index: 4384722 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0445. Min Act: -0.1700
Data Index: 7318015 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0445. Min Act: -0.1700
Data Index: 2807757 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0445. Min Act: -0.1700
Data Index: 2807759 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0108. Min Act: -0.1700
Data Index: 1584200 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0277. Min Act: -0.1700
Data Index: 1584199 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0108. Min Act: -0.1700
Data Index: 6560865 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1450. Min Range: -2.1450
Max Act: 2.0108. Min Act: -0.1700
Data Index: 5716638 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1450. Min Range: -2.1450
Max Act: 1.9939. Min Act: -0.1700
Data Index: 5716634 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1450. Min Range: -2.1450
Max Act: 1.9939. Min Act: -0.1700
Data Index: 2807760 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1450. Min Range: -2.1450
Max Act: 1.9770. Min Act: -0.1700
Data Index: 7811463 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1450. Min Range: -2.1450
Max Act: 1.9770. Min Act: -0.1700
Data Index: 3750154 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1450. Min Range: -2.1450
Max Act: 1.9770. Min Act: -0.1700
Data Index: 6560864 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1450. Min Range: -2.1450
Max Act: 1.9770. Min Act: -0.1700
Data Index: 5716639 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1450. Min Range: -2.1450
Max Act: 1.9600. Min Act: -0.1700
Data Index: 5177471 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19