Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3705 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.2300. Min Act: -0.1700
Data Index: 489173 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1987. Min Act: -0.1700
Data Index: 2786039 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1674. Min Act: -0.1700
Data Index: 6961048 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1362. Min Act: -0.1700
Data Index: 6017415 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 3564677 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1049. Min Act: -0.1700
Data Index: 8309566 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1362. Min Act: -0.1700
Data Index: 3383993 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1362. Min Act: -0.1700
Data Index: 8691371 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1049. Min Act: -0.1700
Data Index: 1035579 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1049. Min Act: -0.1700
Data Index: 7626639 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1049. Min Act: -0.1700
Data Index: 6698505 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 3319091 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 8505654 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 5964161 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 1007297 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 644299 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.1049. Min Act: -0.1700
Data Index: 4113635 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 136238 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0424. Min Act: -0.1700
Data Index: 2953883 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2300. Min Range: -4.2300
Max Act: 4.0737. Min Act: -0.1700
Data Index: 669666 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19