Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1465. Min Range: -6.1465
Max Act: 6.1465. Min Act: -0.1700
Data Index: 4421577 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1465. Min Range: -6.1465
Max Act: 6.0840. Min Act: -0.1700
Data Index: 941292 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.8653. Min Act: -0.1700
Data Index: 3701618 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.8340. Min Act: -0.1700
Data Index: 7852499 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.8028. Min Act: -0.1700
Data Index: 5219287 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.8340. Min Act: -0.1700
Data Index: 3267713 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.8028. Min Act: -0.1700
Data Index: 8137232 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.8028. Min Act: -0.1700
Data Index: 8134381 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.8028. Min Act: -0.1700
Data Index: 8693946 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.7403. Min Act: -0.1700
Data Index: 517325 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.7403. Min Act: -0.1700
Data Index: 8580051 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6778. Min Act: -0.1700
Data Index: 5718114 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6778. Min Act: -0.1700
Data Index: 7869981 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6778. Min Act: -0.1700
Data Index: 271543 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6778. Min Act: -0.1700
Data Index: 5923572 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6465. Min Act: -0.1700
Data Index: 4825023 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6153. Min Act: -0.1700
Data Index: 1992492 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6778. Min Act: -0.1700
Data Index: 5868049 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6465. Min Act: -0.1700
Data Index: 5920559 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1465. Min Range: -6.1465
Max Act: 5.6778. Min Act: -0.1700
Data Index: 3841800 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19