Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2031 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.6578. Min Act: -0.1700
Data Index: 4913684 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.5953. Min Act: -0.1700
Data Index: 8431689 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.4703. Min Act: -0.1700
Data Index: 2812555 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2828. Min Act: -0.1700
Data Index: 304207 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.3453. Min Act: -0.1700
Data Index: 4222343 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.3453. Min Act: -0.1700
Data Index: 5489602 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.3453. Min Act: -0.1700
Data Index: 7398416 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.3453. Min Act: -0.1700
Data Index: 1053022 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2828. Min Act: -0.1700
Data Index: 3609180 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2828. Min Act: -0.1700
Data Index: 5122843 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2828. Min Act: -0.1700
Data Index: 1200485 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.3453. Min Act: -0.1700
Data Index: 1620439 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2203. Min Act: -0.1700
Data Index: 3864143 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2203. Min Act: -0.1700
Data Index: 2331155 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.1578. Min Act: -0.1700
Data Index: 8483878 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2828. Min Act: -0.1700
Data Index: 5997939 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.2203. Min Act: -0.1700
Data Index: 7501744 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.1578. Min Act: -0.1700
Data Index: 7593429 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.1578. Min Act: -0.1700
Data Index: 3414690 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6578. Min Range: -9.6578
Max Act: 9.1578. Min Act: -0.1700
Data Index: 7259774 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19