Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1817. Min Range: -5.1817
Max Act: 5.1817. Min Act: -0.1700
Data Index: 2101477 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1817. Min Range: -5.1817
Max Act: 5.1192. Min Act: -0.1700
Data Index: 4151905 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1817. Min Range: -5.1817
Max Act: 5.0567. Min Act: -0.1700
Data Index: 4375422 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1817. Min Range: -5.1817
Max Act: 5.0255. Min Act: -0.1700
Data Index: 7341084 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9630. Min Act: -0.1700
Data Index: 3167507 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9317. Min Act: -0.1700
Data Index: 8397164 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9317. Min Act: -0.1700
Data Index: 308316 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9317. Min Act: -0.1700
Data Index: 255865 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9317. Min Act: -0.1700
Data Index: 8286211 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9005. Min Act: -0.1700
Data Index: 6406400 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9005. Min Act: -0.1700
Data Index: 7091323 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8692. Min Act: -0.1700
Data Index: 7756263 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8380. Min Act: -0.1700
Data Index: 3490603 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.9005. Min Act: -0.1700
Data Index: 2253199 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8380. Min Act: -0.1700
Data Index: 5684475 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8380. Min Act: -0.1700
Data Index: 2365265 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8380. Min Act: -0.1700
Data Index: 8612318 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8380. Min Act: -0.1700
Data Index: 6665825 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8380. Min Act: -0.1700
Data Index: 5662618 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1817. Min Range: -5.1817
Max Act: 4.8067. Min Act: -0.1700
Data Index: 765483 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19