Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1184 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.6527. Min Act: -0.1700
Data Index: 5939335 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.6214. Min Act: -0.1700
Data Index: 7258385 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.5902. Min Act: -0.1700
Data Index: 11432 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.4964. Min Act: -0.1700
Data Index: 2312455 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.4964. Min Act: -0.1700
Data Index: 4774698 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.4652. Min Act: -0.1700
Data Index: 3601293 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.4339. Min Act: -0.1700
Data Index: 8085893 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.4339. Min Act: -0.1700
Data Index: 2149337 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.4027. Min Act: -0.1700
Data Index: 8350763 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.3402. Min Act: -0.1700
Data Index: 8829160 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.3714. Min Act: -0.1700
Data Index: 4841881 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.3402. Min Act: -0.1700
Data Index: 6344178 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.3714. Min Act: -0.1700
Data Index: 7593101 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.2777. Min Act: -0.1700
Data Index: 5859940 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.3089. Min Act: -0.1700
Data Index: 3338571 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.2464. Min Act: -0.1700
Data Index: 5368530 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.2464. Min Act: -0.1700
Data Index: 5586038 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.2777. Min Act: -0.1700
Data Index: 3127551 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.2777. Min Act: -0.1700
Data Index: 8808117 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6527. Min Range: -5.6527
Max Act: 5.2464. Min Act: -0.1700
Data Index: 5118087 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19