Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 581 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1840. Min Range: -7.1840
Max Act: 7.1840. Min Act: -0.1700
Data Index: 7737304 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1840. Min Range: -7.1840
Max Act: 7.0278. Min Act: -0.1700
Data Index: 7488802 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1840. Min Range: -7.1840
Max Act: 7.0278. Min Act: -0.1700
Data Index: 5944289 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9965. Min Act: -0.1700
Data Index: 454231 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9965. Min Act: -0.1700
Data Index: 4275094 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9653. Min Act: -0.1700
Data Index: 3596920 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9653. Min Act: -0.1700
Data Index: 6851731 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9653. Min Act: -0.1700
Data Index: 6663992 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9653. Min Act: -0.1700
Data Index: 1964594 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9028. Min Act: -0.1700
Data Index: 683834 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9028. Min Act: -0.1700
Data Index: 7233224 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9028. Min Act: -0.1700
Data Index: 4418177 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.8403. Min Act: -0.1700
Data Index: 2596028 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.8715. Min Act: -0.1700
Data Index: 1996937 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.9028. Min Act: -0.1700
Data Index: 5072081 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.8715. Min Act: -0.1700
Data Index: 3358511 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.8715. Min Act: -0.1700
Data Index: 3939599 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.8090. Min Act: -0.1700
Data Index: 4570384 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.8090. Min Act: -0.1700
Data Index: 6085593 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1840. Min Range: -7.1840
Max Act: 6.8090. Min Act: -0.1700
Data Index: 8515817 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19