Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 473 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0151. Min Range: -4.0151
Max Act: 4.0151. Min Act: -0.1700
Data Index: 8257813 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.9213. Min Act: -0.1700
Data Index: 3383874 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.9525. Min Act: -0.1700
Data Index: 6792320 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.8275. Min Act: -0.1700
Data Index: 336338 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.8587. Min Act: -0.1700
Data Index: 7411281 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.8587. Min Act: -0.1700
Data Index: 3549233 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.8587. Min Act: -0.1700
Data Index: 3889201 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7962. Min Act: -0.1700
Data Index: 4375791 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7962. Min Act: -0.1700
Data Index: 2657098 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7962. Min Act: -0.1700
Data Index: 3642173 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7962. Min Act: -0.1700
Data Index: 7789750 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7649. Min Act: -0.1699
Data Index: 3902382 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7336. Min Act: -0.1700
Data Index: 5676721 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.6711. Min Act: -0.1700
Data Index: 222549 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7336. Min Act: -0.1700
Data Index: 6981329 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7336. Min Act: -0.1700
Data Index: 7413303 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7962. Min Act: -0.1700
Data Index: 5697885 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7336. Min Act: -0.1700
Data Index: 924362 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7649. Min Act: -0.1700
Data Index: 3840421 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0151. Min Range: -4.0151
Max Act: 3.7962. Min Act: -0.1700
Data Index: 5042956 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19