Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1439 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.4406. Min Act: -0.1681
Data Index: 600467 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.4054. Min Act: -0.1699
Data Index: 2252326 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.4054. Min Act: -0.1699
Data Index: 4128993 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3878. Min Act: -0.1700
Data Index: 1184877 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3701. Min Act: -0.1700
Data Index: 4204969 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3790. Min Act: -0.1688
Data Index: 7445478 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3701. Min Act: -0.1700
Data Index: 311873 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3525. Min Act: -0.1699
Data Index: 3824236 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3613. Min Act: -0.1700
Data Index: 3397364 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3613. Min Act: -0.1700
Data Index: 6858653 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3613. Min Act: -0.1700
Data Index: 2492088 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3701. Min Act: -0.1698
Data Index: 8709733 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3613. Min Act: -0.1700
Data Index: 5092215 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3437. Min Act: -0.1700
Data Index: 312367 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3437. Min Act: -0.1700
Data Index: 8239601 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3349. Min Act: -0.1691
Data Index: 7287056 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3437. Min Act: -0.1700
Data Index: 904523 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3437. Min Act: -0.1700
Data Index: 6873672 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3525. Min Act: -0.1700
Data Index: 6465468 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4406. Min Range: -1.4406
Max Act: 1.3437. Min Act: -0.1700
Data Index: 6317176 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19