Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 634 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.3013. Min Act: -0.1700
Data Index: 5525892 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.2701. Min Act: -0.1700
Data Index: 7951278 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.2076. Min Act: -0.1700
Data Index: 8025433 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.0513. Min Act: -0.1700
Data Index: 5894089 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.0513. Min Act: -0.1700
Data Index: 1669330 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.1138. Min Act: -0.1700
Data Index: 2243247 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 5634164 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9888. Min Act: -0.1700
Data Index: 1879322 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.0201. Min Act: -0.1700
Data Index: 8640972 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9888. Min Act: -0.1700
Data Index: 6684094 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 2338905 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 3278946 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 8717248 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 2579497 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9576. Min Act: -0.1700
Data Index: 541168 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 7073315 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 5866426 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.8638. Min Act: -0.1700
Data Index: 1352653 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.8638. Min Act: -0.1700
Data Index: 3523173 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.8951. Min Act: -0.1700
Data Index: 1005207 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19