Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1297. Min Range: -7.1297
Max Act: 7.1297. Min Act: -0.1700
Data Index: 263220 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1297. Min Range: -7.1297
Max Act: 7.0359. Min Act: -0.1700
Data Index: 5864890 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1297. Min Range: -7.1297
Max Act: 7.0672. Min Act: -0.1700
Data Index: 6003241 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1297. Min Range: -7.1297
Max Act: 7.0047. Min Act: -0.1700
Data Index: 2936267 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.9109. Min Act: -0.1700
Data Index: 830259 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.8797. Min Act: -0.1700
Data Index: 4663523 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.8172. Min Act: -0.1700
Data Index: 6368596 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.8172. Min Act: -0.1700
Data Index: 8513785 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.8172. Min Act: -0.1700
Data Index: 1984006 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.8172. Min Act: -0.1700
Data Index: 674484 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.7859. Min Act: -0.1700
Data Index: 2002260 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.7859. Min Act: -0.1700
Data Index: 549070 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.7547. Min Act: -0.1700
Data Index: 5606008 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.7234. Min Act: -0.1700
Data Index: 6196645 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.7547. Min Act: -0.1700
Data Index: 640062 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.6922. Min Act: -0.1700
Data Index: 5359582 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.6922. Min Act: -0.1700
Data Index: 4547238 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.6922. Min Act: -0.1700
Data Index: 4375098 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.7234. Min Act: -0.1700
Data Index: 5458183 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1297. Min Range: -7.1297
Max Act: 6.6609. Min Act: -0.1700
Data Index: 53105 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19