Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3506. Min Act: -0.1663
Data Index: 6909316 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3418. Min Act: -0.1676
Data Index: 240865 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3241. Min Act: -0.1699
Data Index: 4477236 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3153. Min Act: -0.1641
Data Index: 4656235 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3065. Min Act: -0.1307
Data Index: 7013501 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3065. Min Act: -0.1586
Data Index: 2361350 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3065. Min Act: -0.1691
Data Index: 1641372 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2977. Min Act: -0.1697
Data Index: 7025462 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3065. Min Act: -0.1641
Data Index: 3773382 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2977. Min Act: -0.1340
Data Index: 4034273 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2977. Min Act: -0.1253
Data Index: 7148375 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2888. Min Act: -0.1584
Data Index: 6391536 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2977. Min Act: -0.1629
Data Index: 3546932 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2800. Min Act: -0.1700
Data Index: 1534144 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2888. Min Act: -0.1635
Data Index: 4602344 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2888. Min Act: -0.1700
Data Index: 2940577 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2624. Min Act: -0.1644
Data Index: 3497655 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2712. Min Act: -0.1697
Data Index: 5211009 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2800. Min Act: -0.1522
Data Index: 3356043 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2712. Min Act: -0.1493
Data Index: 3834403 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19