Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.5393. Min Act: -0.1700
Data Index: 1821586 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.4768. Min Act: -0.1700
Data Index: 5717255 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.4143. Min Act: -0.1700
Data Index: 678720 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.3518. Min Act: -0.1700
Data Index: 6552403 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.2580. Min Act: -0.1700
Data Index: 4157798 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.3205. Min Act: -0.1700
Data Index: 3470024 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.2893. Min Act: -0.1700
Data Index: 7305791 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.2580. Min Act: -0.1700
Data Index: 2320337 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.2268. Min Act: -0.1700
Data Index: 3028944 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.1330. Min Act: -0.1700
Data Index: 3203001 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.1018. Min Act: -0.1700
Data Index: 8275043 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.1643. Min Act: -0.1700
Data Index: 8187843 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.1018. Min Act: -0.1700
Data Index: 3637392 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.1330. Min Act: -0.1700
Data Index: 1316654 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.1018. Min Act: -0.1700
Data Index: 5694900 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.0705. Min Act: -0.1700
Data Index: 7332209 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.0393. Min Act: -0.1700
Data Index: 4812755 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.0705. Min Act: -0.1700
Data Index: 7211717 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.0393. Min Act: -0.1700
Data Index: 5075944 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5393. Min Range: -7.5393
Max Act: 7.0393. Min Act: -0.1700
Data Index: 6789764 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19