Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 97 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.3083. Min Act: -0.1700
Data Index: 4911055 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1984. Min Act: -0.1700
Data Index: 4436450 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1826. Min Act: -0.1700
Data Index: 2179879 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1984. Min Act: -0.1700
Data Index: 5809000 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.2141. Min Act: -0.1700
Data Index: 1817233 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1669. Min Act: -0.1700
Data Index: 4296051 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1984. Min Act: -0.1700
Data Index: 6064622 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1826. Min Act: -0.1700
Data Index: 5363355 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1984. Min Act: -0.1700
Data Index: 5502850 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1826. Min Act: -0.1700
Data Index: 7529545 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1984. Min Act: -0.1700
Data Index: 8178519 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1984. Min Act: -0.1700
Data Index: 4319551 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1984. Min Act: -0.1700
Data Index: 6674075 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1512. Min Act: -0.1700
Data Index: 5165215 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1669. Min Act: -0.1700
Data Index: 311565 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1669. Min Act: -0.1700
Data Index: 1133311 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1669. Min Act: -0.1700
Data Index: 2719578 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1669. Min Act: -0.1700
Data Index: 3229732 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1512. Min Act: -0.1700
Data Index: 2128085 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3083. Min Range: -3.3083
Max Act: 3.1354. Min Act: -0.1700
Data Index: 4400955 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19