Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 776 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.7191. Min Act: -0.1700
Data Index: 4395956 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.7105. Min Act: -0.1700
Data Index: 5617618 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6931. Min Act: -0.1700
Data Index: 3221011 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6758. Min Act: -0.1700
Data Index: 8768075 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6671. Min Act: -0.1700
Data Index: 3088345 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6497. Min Act: -0.1700
Data Index: 7262626 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6497. Min Act: -0.1700
Data Index: 8768079 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6410. Min Act: -0.1700
Data Index: 4640851 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6235. Min Act: -0.1700
Data Index: 5591486 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6235. Min Act: -0.1700
Data Index: 3903442 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6148. Min Act: -0.1699
Data Index: 86620 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6235. Min Act: -0.1700
Data Index: 5125594 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6323. Min Act: -0.1700
Data Index: 556880 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6061. Min Act: -0.1700
Data Index: 3932970 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.5974. Min Act: -0.1700
Data Index: 328301 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6148. Min Act: -0.1699
Data Index: 6877446 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6061. Min Act: -0.1700
Data Index: 7804632 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.6061. Min Act: -0.1700
Data Index: 3903439 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.5974. Min Act: -0.1700
Data Index: 1474197 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7191. Min Range: -1.7191
Max Act: 1.5974. Min Act: -0.1693
Data Index: 2340823 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19