Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.4543. Min Act: -0.1700
Data Index: 1758473 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.4230. Min Act: -0.1700
Data Index: 5221368 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.2355. Min Act: -0.1700
Data Index: 6034627 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.2355. Min Act: -0.1700
Data Index: 2725897 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.2668. Min Act: -0.1700
Data Index: 2061293 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.2043. Min Act: -0.1700
Data Index: 4202669 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.2043. Min Act: -0.1700
Data Index: 6471434 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.2043. Min Act: -0.1700
Data Index: 2684436 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.1730. Min Act: -0.1700
Data Index: 3345979 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.1730. Min Act: -0.1700
Data Index: 5573139 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.1418. Min Act: -0.1700
Data Index: 2684437 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0793. Min Act: -0.1700
Data Index: 8213184 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0480. Min Act: -0.1700
Data Index: 5100442 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0168. Min Act: -0.1700
Data Index: 4349451 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0480. Min Act: -0.1700
Data Index: 4257656 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0480. Min Act: -0.1700
Data Index: 3681607 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0168. Min Act: -0.1700
Data Index: 1219115 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0480. Min Act: -0.1700
Data Index: 3179403 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4543. Min Range: -6.4543
Max Act: 5.9855. Min Act: -0.1700
Data Index: 2116346 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4543. Min Range: -6.4543
Max Act: 6.0168. Min Act: -0.1700
Data Index: 2209501 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19