Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1550 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0518. Min Range: -7.0518
Max Act: 7.0518. Min Act: -0.1700
Data Index: 606816 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.9893. Min Act: -0.1700
Data Index: 7889009 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.9268. Min Act: -0.1700
Data Index: 848706 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.9268. Min Act: -0.1700
Data Index: 794828 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.8956. Min Act: -0.1700
Data Index: 5555135 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.8331. Min Act: -0.1700
Data Index: 7788894 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.8331. Min Act: -0.1700
Data Index: 7622429 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.8018. Min Act: -0.1700
Data Index: 1463880 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.7393. Min Act: -0.1700
Data Index: 375118 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.7393. Min Act: -0.1700
Data Index: 7911837 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.7393. Min Act: -0.1700
Data Index: 1639717 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.7393. Min Act: -0.1700
Data Index: 4243923 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.7706. Min Act: -0.1700
Data Index: 2642065 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.7081. Min Act: -0.1700
Data Index: 5677654 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.6768. Min Act: -0.1700
Data Index: 5303115 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.6143. Min Act: -0.1700
Data Index: 8624407 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.5518. Min Act: -0.1700
Data Index: 4318584 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.5518. Min Act: -0.1700
Data Index: 1228894 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.5518. Min Act: -0.1700
Data Index: 7284306 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0518. Min Range: -7.0518
Max Act: 6.5518. Min Act: -0.1700
Data Index: 2808410 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19