Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1595 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.3038. Min Act: -0.1700
Data Index: 2820784 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.0538. Min Act: -0.1700
Data Index: 4022049 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.9913. Min Act: -0.1700
Data Index: 1112195 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.9601. Min Act: -0.1700
Data Index: 3828495 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 1853796 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7413. Min Act: -0.1700
Data Index: 6351447 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 1425235 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 249390 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 530985 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 2222418 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 6844193 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 3225237 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7413. Min Act: -0.1700
Data Index: 1530328 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 1045696 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 3304673 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 7018306 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7101. Min Act: -0.1700
Data Index: 5051794 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 4286103 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 1251383 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7101. Min Act: -0.1700
Data Index: 6067226 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19