Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.9705. Min Act: -0.1700
Data Index: 178138 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.7517. Min Act: -0.1700
Data Index: 5853166 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.5955. Min Act: -0.1700
Data Index: 194888 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.6580. Min Act: -0.1700
Data Index: 3123871 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.6580. Min Act: -0.1700
Data Index: 7405325 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.5955. Min Act: -0.1700
Data Index: 7918540 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.5955. Min Act: -0.1700
Data Index: 5659487 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.6267. Min Act: -0.1700
Data Index: 1397873 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4392. Min Act: -0.1700
Data Index: 2979709 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4705. Min Act: -0.1700
Data Index: 681588 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.5017. Min Act: -0.1700
Data Index: 8079476 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.5017. Min Act: -0.1700
Data Index: 7162376 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.5330. Min Act: -0.1700
Data Index: 6404409 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4705. Min Act: -0.1700
Data Index: 6938019 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.3767. Min Act: -0.1700
Data Index: 2104325 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4705. Min Act: -0.1700
Data Index: 7432903 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4080. Min Act: -0.1700
Data Index: 7162681 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4392. Min Act: -0.1700
Data Index: 3999480 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4705. Min Act: -0.1700
Data Index: 6154768 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9705. Min Range: -6.9705
Max Act: 6.4392. Min Act: -0.1700
Data Index: 4099398 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19