Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1154. Min Range: -12.1154
Max Act: 12.1154. Min Act: -0.1700
Data Index: 8224640 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1154. Min Range: -12.1154
Max Act: 11.0529. Min Act: -0.1700
Data Index: 1270178 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.9904. Min Act: -0.1700
Data Index: 180407 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.7404. Min Act: -0.1700
Data Index: 7323648 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.6154. Min Act: -0.1700
Data Index: 4963231 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.5529. Min Act: -0.1700
Data Index: 345042 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.2404. Min Act: -0.1700
Data Index: 6940525 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.1154. Min Act: -0.1700
Data Index: 1795395 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.0529. Min Act: -0.1700
Data Index: 8326279 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.1154. Min Act: -0.1700
Data Index: 4824517 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9904. Min Act: -0.1700
Data Index: 2396957 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9904. Min Act: -0.1700
Data Index: 5545527 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9904. Min Act: -0.1700
Data Index: 6743541 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1154. Min Range: -12.1154
Max Act: 10.0529. Min Act: -0.1700
Data Index: 4648712 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9904. Min Act: -0.1700
Data Index: 5611642 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9279. Min Act: -0.1700
Data Index: 4631851 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9904. Min Act: -0.1700
Data Index: 6265625 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.8654. Min Act: -0.1700
Data Index: 6317242 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9279. Min Act: -0.1700
Data Index: 7061568 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1154. Min Range: -12.1154
Max Act: 9.9279. Min Act: -0.1700
Data Index: 1564288 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19