Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 302 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.3042. Min Act: -0.1700
Data Index: 1449334 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.2730. Min Act: -0.1700
Data Index: 7622904 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.2730. Min Act: -0.1700
Data Index: 8005780 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.2730. Min Act: -0.1700
Data Index: 4717723 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.2105. Min Act: -0.1700
Data Index: 3173548 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 426756 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 7205812 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1798085 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 6913885 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.2105. Min Act: -0.1700
Data Index: 8739870 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.2417. Min Act: -0.1700
Data Index: 4856047 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 6255909 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 403893 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 1709274 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 6779686 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 3172368 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 350809 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 4071242 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1167. Min Act: -0.1700
Data Index: 2884202 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3042. Min Range: -4.3042
Max Act: 4.1792. Min Act: -0.1700
Data Index: 4609238 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19