Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 889 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9851. Min Act: -0.1700
Data Index: 6880479 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9851. Min Act: -0.1700
Data Index: 5977663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9851. Min Act: -0.1648
Data Index: 6880473 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9682. Min Act: -0.1151
Data Index: 6880478 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9682. Min Act: -0.1368
Data Index: 6880474 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9342. Min Act: -0.1700
Data Index: 6531790 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9342. Min Act: -0.1700
Data Index: 6308558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9342. Min Act: -0.1700
Data Index: 7276862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9002. Min Act: -0.1700
Data Index: 6924179 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9002. Min Act: -0.1700
Data Index: 208258 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9172. Min Act: -0.1700
Data Index: 5819317 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.8831. Min Act: -0.1700
Data Index: 4093904 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9002. Min Act: -0.1699
Data Index: 659819 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.8831. Min Act: -0.1700
Data Index: 6880477 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.9002. Min Act: -0.1700
Data Index: 588706 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.8660. Min Act: -0.1700
Data Index: 5612384 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.8831. Min Act: -0.1700
Data Index: 5978027 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.8831. Min Act: -0.1700
Data Index: 2287535 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.8660. Min Act: -0.1700
Data Index: 6815383 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9851. Min Range: -1.9851
Max Act: 1.8660. Min Act: -0.1700
Data Index: 488364 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19