Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.8094. Min Act: -0.1700
Data Index: 1710292 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.8094. Min Act: -0.1700
Data Index: 1303086 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.8094. Min Act: -0.1700
Data Index: 5023564 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.6686. Min Act: -0.1700
Data Index: 444051 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.6843. Min Act: -0.1700
Data Index: 6522930 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.6843. Min Act: -0.1700
Data Index: 2603212 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.6686. Min Act: -0.1700
Data Index: 8339463 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.6373. Min Act: -0.1700
Data Index: 2545934 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.5904. Min Act: -0.1700
Data Index: 356680 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.5747. Min Act: -0.1700
Data Index: 7298406 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.5121. Min Act: -0.1700
Data Index: 2650755 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4964. Min Act: -0.1700
Data Index: 1838155 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4808. Min Act: -0.1700
Data Index: 3077073 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.5121. Min Act: -0.1700
Data Index: 7443342 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4964. Min Act: -0.1700
Data Index: 8298864 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4338. Min Act: -0.1700
Data Index: 2796371 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4651. Min Act: -0.1700
Data Index: 6028688 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4808. Min Act: -0.1700
Data Index: 5759293 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4651. Min Act: -0.1700
Data Index: 137472 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8094. Min Range: -3.8094
Max Act: 3.4181. Min Act: -0.1700
Data Index: 2020767 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19