Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1352 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.1439. Min Act: -0.1700
Data Index: 1814185 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.1439. Min Act: -0.1700
Data Index: 3742117 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.1439. Min Act: -0.1700
Data Index: 8076563 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.0502. Min Act: -0.1700
Data Index: 6389463 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.0189. Min Act: -0.1700
Data Index: 2129184 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.0502. Min Act: -0.1700
Data Index: 3566527 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.0502. Min Act: -0.1700
Data Index: 1987650 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.0189. Min Act: -0.1700
Data Index: 1814186 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9564. Min Act: -0.1700
Data Index: 7813524 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9877. Min Act: -0.1700
Data Index: 4648001 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9877. Min Act: -0.1700
Data Index: 1127274 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1439. Min Range: -4.1439
Max Act: 4.0189. Min Act: -0.1700
Data Index: 4196977 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9877. Min Act: -0.1700
Data Index: 257977 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9877. Min Act: -0.1700
Data Index: 7227306 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9564. Min Act: -0.1700
Data Index: 3288954 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9564. Min Act: -0.1700
Data Index: 1654644 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9564. Min Act: -0.1700
Data Index: 4812937 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9564. Min Act: -0.1700
Data Index: 107439 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9564. Min Act: -0.1700
Data Index: 4658102 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1439. Min Range: -4.1439
Max Act: 3.9564. Min Act: -0.1700
Data Index: 3597136 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19