Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1211 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0889. Min Range: -6.0889
Max Act: 6.0889. Min Act: -0.1700
Data Index: 164123 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0889. Min Range: -6.0889
Max Act: 6.0576. Min Act: -0.1700
Data Index: 4762943 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0889. Min Range: -6.0889
Max Act: 6.0264. Min Act: -0.1700
Data Index: 6517087 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0889. Min Range: -6.0889
Max Act: 6.0264. Min Act: -0.1700
Data Index: 1696022 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.9639. Min Act: -0.1700
Data Index: 3391183 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8701. Min Act: -0.1700
Data Index: 3887784 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8389. Min Act: -0.1700
Data Index: 1412470 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8389. Min Act: -0.1700
Data Index: 799528 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8389. Min Act: -0.1700
Data Index: 6817588 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8701. Min Act: -0.1700
Data Index: 4342139 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.7764. Min Act: -0.1700
Data Index: 781634 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8076. Min Act: -0.1700
Data Index: 1036157 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8076. Min Act: -0.1700
Data Index: 7698263 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.8076. Min Act: -0.1700
Data Index: 5893283 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.7764. Min Act: -0.1700
Data Index: 6153234 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.7764. Min Act: -0.1700
Data Index: 3511268 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.7451. Min Act: -0.1700
Data Index: 4704969 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.7451. Min Act: -0.1700
Data Index: 164114 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.7139. Min Act: -0.1700
Data Index: 2188021 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0889. Min Range: -6.0889
Max Act: 5.7139. Min Act: -0.1700
Data Index: 5041490 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19