Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3112. Min Range: -7.3112
Max Act: 7.3112. Min Act: -0.1700
Data Index: 855040 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3112. Min Range: -7.3112
Max Act: 7.2800. Min Act: -0.1700
Data Index: 3632566 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3112. Min Range: -7.3112
Max Act: 7.2487. Min Act: -0.1700
Data Index: 1664632 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3112. Min Range: -7.3112
Max Act: 7.1862. Min Act: -0.1700
Data Index: 3100378 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3112. Min Range: -7.3112
Max Act: 7.1862. Min Act: -0.1700
Data Index: 4667484 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3112. Min Range: -7.3112
Max Act: 7.0612. Min Act: -0.1700
Data Index: 3313132 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.9987. Min Act: -0.1700
Data Index: 3978507 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.9675. Min Act: -0.1700
Data Index: 2936796 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.9362. Min Act: -0.1700
Data Index: 3419156 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.9050. Min Act: -0.1700
Data Index: 6763438 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.8425. Min Act: -0.1700
Data Index: 8823746 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.8112. Min Act: -0.1700
Data Index: 762892 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.8425. Min Act: -0.1700
Data Index: 5992188 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.8112. Min Act: -0.1700
Data Index: 4935660 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.8112. Min Act: -0.1700
Data Index: 4362350 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.8112. Min Act: -0.1700
Data Index: 7258474 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.8112. Min Act: -0.1700
Data Index: 3125756 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.7175. Min Act: -0.1700
Data Index: 2863255 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.7487. Min Act: -0.1700
Data Index: 375412 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3112. Min Range: -7.3112
Max Act: 6.7487. Min Act: -0.1700
Data Index: 1099682 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19