Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1258 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6008. Min Range: -6.6008
Max Act: 6.6008. Min Act: -0.1700
Data Index: 6304798 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6008. Min Range: -6.6008
Max Act: 6.3821. Min Act: -0.1700
Data Index: 4813789 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6008. Min Range: -6.6008
Max Act: 6.2258. Min Act: -0.1700
Data Index: 4270527 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6008. Min Range: -6.6008
Max Act: 6.1008. Min Act: -0.1700
Data Index: 1097039 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6008. Min Range: -6.6008
Max Act: 6.0383. Min Act: -0.1700
Data Index: 1353515 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6008. Min Range: -6.6008
Max Act: 6.0071. Min Act: -0.1700
Data Index: 6060863 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.9446. Min Act: -0.1700
Data Index: 5979955 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.9446. Min Act: -0.1700
Data Index: 5723005 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.9133. Min Act: -0.1700
Data Index: 7059874 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.8821. Min Act: -0.1700
Data Index: 7961668 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.8821. Min Act: -0.1700
Data Index: 7120145 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.8508. Min Act: -0.1700
Data Index: 2944001 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.8821. Min Act: -0.1700
Data Index: 2197348 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.8508. Min Act: -0.1700
Data Index: 4505836 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.7883. Min Act: -0.1700
Data Index: 1426392 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.7571. Min Act: -0.1700
Data Index: 4157740 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.7571. Min Act: -0.1700
Data Index: 8133070 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.7571. Min Act: -0.1700
Data Index: 5717937 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.7571. Min Act: -0.1700
Data Index: 2819642 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6008. Min Range: -6.6008
Max Act: 5.7571. Min Act: -0.1700
Data Index: 7044900 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19