Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5283 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0330. Min Range: -3.0330
Max Act: 3.0330. Min Act: -0.1700
Data Index: 4836468 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0330. Min Range: -3.0330
Max Act: 3.0015. Min Act: -0.1700
Data Index: 8352829 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.9698. Min Act: -0.1700
Data Index: 3717763 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.9540. Min Act: -0.1700
Data Index: 7069306 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.9698. Min Act: -0.1700
Data Index: 3096084 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.9223. Min Act: -0.1700
Data Index: 8432164 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.9223. Min Act: -0.1700
Data Index: 4581721 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.9065. Min Act: -0.1700
Data Index: 7130600 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8906. Min Act: -0.1700
Data Index: 8553016 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8906. Min Act: -0.1700
Data Index: 3116722 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8748. Min Act: -0.1700
Data Index: 893725 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8748. Min Act: -0.1700
Data Index: 8549120 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8430. Min Act: -0.1700
Data Index: 668269 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8906. Min Act: -0.1700
Data Index: 6118708 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8906. Min Act: -0.1700
Data Index: 2171001 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8589. Min Act: -0.1700
Data Index: 8815582 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8589. Min Act: -0.1700
Data Index: 508029 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8430. Min Act: -0.1700
Data Index: 5648869 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8589. Min Act: -0.1700
Data Index: 6952888 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0330. Min Range: -3.0330
Max Act: 2.8430. Min Act: -0.1700
Data Index: 3320340 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19