Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6887. Min Act: -0.1699
Data Index: 7156269 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6713. Min Act: -0.1700
Data Index: 1208737 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6713. Min Act: -0.1696
Data Index: 2174947 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6626. Min Act: -0.1688
Data Index: 7206219 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6626. Min Act: -0.1700
Data Index: 5149083 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6626. Min Act: -0.1699
Data Index: 803384 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6452. Min Act: -0.1579
Data Index: 451624 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6540. Min Act: -0.1700
Data Index: 2350499 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6452. Min Act: -0.1673
Data Index: 1208741 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6452. Min Act: -0.1700
Data Index: 5757448 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6540. Min Act: -0.1700
Data Index: 1337899 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6540. Min Act: -0.1696
Data Index: 5335483 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6365. Min Act: -0.1700
Data Index: 2130052 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6365. Min Act: -0.1672
Data Index: 4952176 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6278. Min Act: -0.1699
Data Index: 7721659 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6278. Min Act: -0.1696
Data Index: 4337906 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6278. Min Act: -0.1697
Data Index: 418173 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6191. Min Act: -0.1695
Data Index: 4356541 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6278. Min Act: -0.1699
Data Index: 2427976 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6887. Min Range: -1.6887
Max Act: 1.6278. Min Act: -0.1683
Data Index: 5144132 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19