Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.4658. Min Act: -0.1700
Data Index: 1385842 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.4345. Min Act: -0.1700
Data Index: 3917679 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.4033. Min Act: -0.1700
Data Index: 5080022 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.4033. Min Act: -0.1700
Data Index: 6892416 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.4345. Min Act: -0.1700
Data Index: 6038217 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.4033. Min Act: -0.1700
Data Index: 1385843 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.4033. Min Act: -0.1700
Data Index: 2981994 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3720. Min Act: -0.1700
Data Index: 3034549 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1981369 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3408. Min Act: -0.1700
Data Index: 5941364 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3095. Min Act: -0.1700
Data Index: 1630770 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3408. Min Act: -0.1700
Data Index: 6469157 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3720. Min Act: -0.1700
Data Index: 5819224 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3408. Min Act: -0.1700
Data Index: 2981995 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.2470. Min Act: -0.1700
Data Index: 7683179 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3095. Min Act: -0.1700
Data Index: 5080021 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.3408. Min Act: -0.1700
Data Index: 1541073 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.2783. Min Act: -0.1700
Data Index: 4939700 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.2783. Min Act: -0.1700
Data Index: 4646858 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4658. Min Range: -6.4658
Max Act: 6.2470. Min Act: -0.1700
Data Index: 5478695 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19