Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5132 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1136. Min Range: -7.1136
Max Act: 7.1136. Min Act: -0.1700
Data Index: 2789552 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.8636. Min Act: -0.1700
Data Index: 396648 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.8636. Min Act: -0.1700
Data Index: 7808326 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.7699. Min Act: -0.1700
Data Index: 6277368 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.7699. Min Act: -0.1700
Data Index: 1318619 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.7386. Min Act: -0.1700
Data Index: 3075603 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.7386. Min Act: -0.1700
Data Index: 5839396 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.7386. Min Act: -0.1700
Data Index: 7368027 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.7074. Min Act: -0.1700
Data Index: 7690489 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6761. Min Act: -0.1700
Data Index: 4340313 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6761. Min Act: -0.1700
Data Index: 1034100 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6449. Min Act: -0.1700
Data Index: 7547948 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6449. Min Act: -0.1700
Data Index: 8299658 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6449. Min Act: -0.1700
Data Index: 3270048 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6449. Min Act: -0.1700
Data Index: 2531416 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6449. Min Act: -0.1700
Data Index: 2899686 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6761. Min Act: -0.1700
Data Index: 8782075 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6136. Min Act: -0.1700
Data Index: 5770564 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6136. Min Act: -0.1700
Data Index: 8360499 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1136. Min Range: -7.1136
Max Act: 6.6136. Min Act: -0.1700
Data Index: 1815579 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19