Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.6533. Min Act: -0.1700
Data Index: 2926149 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.6533. Min Act: -0.1689
Data Index: 4377447 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.6097. Min Act: -0.1691
Data Index: 6290220 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.6097. Min Act: -0.1686
Data Index: 1406284 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5923. Min Act: -0.1687
Data Index: 7869632 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5923. Min Act: -0.1644
Data Index: 5650089 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5923. Min Act: -0.1692
Data Index: 7360029 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5835. Min Act: -0.1672
Data Index: 5650096 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5748. Min Act: -0.1690
Data Index: 1008578 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5661. Min Act: -0.1700
Data Index: 4948379 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5661. Min Act: -0.1658
Data Index: 3858160 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5573. Min Act: -0.1650
Data Index: 1559348 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5485. Min Act: -0.1638
Data Index: 8254186 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5485. Min Act: -0.1697
Data Index: 8769049 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5573. Min Act: -0.1684
Data Index: 2362926 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5485. Min Act: -0.1695
Data Index: 5167959 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5485. Min Act: -0.1700
Data Index: 5609779 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5573. Min Act: -0.1603
Data Index: 853967 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5485. Min Act: -0.1694
Data Index: 2725103 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6533. Min Range: -1.6533
Max Act: 1.5485. Min Act: -0.1693
Data Index: 4464193 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19