Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.6203. Min Act: -0.1700
Data Index: 3090360 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.6203. Min Act: -0.1700
Data Index: 8481952 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.6203. Min Act: -0.1700
Data Index: 4968703 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.5578. Min Act: -0.1700
Data Index: 8766944 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.5265. Min Act: -0.1700
Data Index: 3963956 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.5578. Min Act: -0.1700
Data Index: 5456629 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4953. Min Act: -0.1700
Data Index: 5455702 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4953. Min Act: -0.1700
Data Index: 689430 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4640. Min Act: -0.1700
Data Index: 4926703 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4640. Min Act: -0.1700
Data Index: 99849 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4640. Min Act: -0.1700
Data Index: 6850494 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4328. Min Act: -0.1700
Data Index: 2149245 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4328. Min Act: -0.1700
Data Index: 6878190 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4640. Min Act: -0.1700
Data Index: 891270 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4328. Min Act: -0.1700
Data Index: 3308979 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.3703. Min Act: -0.1700
Data Index: 1081735 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4015. Min Act: -0.1700
Data Index: 6679224 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4015. Min Act: -0.1700
Data Index: 465075 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4015. Min Act: -0.1700
Data Index: 183738 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6203. Min Range: -4.6203
Max Act: 4.4015. Min Act: -0.1700
Data Index: 8370415 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19