Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2553 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.3571. Min Act: -0.1700
Data Index: 2044358 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.3571. Min Act: -0.1700
Data Index: 5294711 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.3408. Min Act: -0.1700
Data Index: 3703009 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.3243. Min Act: -0.1700
Data Index: 7077238 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.3243. Min Act: -0.1700
Data Index: 3230103 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.3079. Min Act: -0.1700
Data Index: 8019256 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.3079. Min Act: -0.1700
Data Index: 5294721 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2915. Min Act: -0.1700
Data Index: 5948738 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2750. Min Act: -0.1700
Data Index: 4819804 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2915. Min Act: -0.1700
Data Index: 4946468 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2750. Min Act: -0.1700
Data Index: 4638127 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2750. Min Act: -0.1700
Data Index: 7763038 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2585. Min Act: -0.1700
Data Index: 974891 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2750. Min Act: -0.1700
Data Index: 5305188 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2750. Min Act: -0.1700
Data Index: 7854967 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2420. Min Act: -0.1700
Data Index: 6390092 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2585. Min Act: -0.1700
Data Index: 3848148 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2585. Min Act: -0.1700
Data Index: 7289638 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2585. Min Act: -0.1700
Data Index: 4806007 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3571. Min Range: -2.3571
Max Act: 2.2585. Min Act: -0.1700
Data Index: 1650556 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19