Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.5260. Min Act: -0.1700
Data Index: 5748818 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.4947. Min Act: -0.1700
Data Index: 3208183 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.4010. Min Act: -0.1700
Data Index: 969024 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.4010. Min Act: -0.1700
Data Index: 4750748 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2447. Min Act: -0.1700
Data Index: 7582025 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2447. Min Act: -0.1700
Data Index: 5332891 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2447. Min Act: -0.1700
Data Index: 8502463 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2447. Min Act: -0.1700
Data Index: 5511269 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2447. Min Act: -0.1700
Data Index: 1781142 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1822. Min Act: -0.1700
Data Index: 7044861 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2135. Min Act: -0.1700
Data Index: 8502462 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2447. Min Act: -0.1700
Data Index: 2291075 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.2135. Min Act: -0.1700
Data Index: 5151535 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6514111 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1822. Min Act: -0.1700
Data Index: 8502465 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1822. Min Act: -0.1700
Data Index: 8502464 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1197. Min Act: -0.1700
Data Index: 2600914 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1510. Min Act: -0.1700
Data Index: 45014 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1510. Min Act: -0.1700
Data Index: 2538226 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5260. Min Range: -5.5260
Max Act: 5.1197. Min Act: -0.1700
Data Index: 384552 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19