Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3470. Min Range: -6.3470
Max Act: 6.3470. Min Act: -0.1700
Data Index: 2506476 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3470. Min Range: -6.3470
Max Act: 6.0657. Min Act: -0.1700
Data Index: 1159907 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.8782. Min Act: -0.1700
Data Index: 5048702 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.8470. Min Act: -0.1700
Data Index: 8477988 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.8157. Min Act: -0.1700
Data Index: 4206636 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.8470. Min Act: -0.1700
Data Index: 5858741 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7845. Min Act: -0.1700
Data Index: 8205595 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7532. Min Act: -0.1700
Data Index: 8424646 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7532. Min Act: -0.1700
Data Index: 655697 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7220. Min Act: -0.1700
Data Index: 8592267 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7220. Min Act: -0.1700
Data Index: 5632749 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7220. Min Act: -0.1700
Data Index: 5401297 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6964225 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.6907. Min Act: -0.1700
Data Index: 2089352 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.7220. Min Act: -0.1700
Data Index: 2078191 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.6595. Min Act: -0.1700
Data Index: 8043008 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.6907. Min Act: -0.1700
Data Index: 8786032 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.6282. Min Act: -0.1700
Data Index: 4185124 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.6282. Min Act: -0.1700
Data Index: 1417147 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3470. Min Range: -6.3470
Max Act: 5.6595. Min Act: -0.1700
Data Index: 1162608 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19