Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1335. Min Range: -9.1335
Max Act: 9.1335. Min Act: -0.1700
Data Index: 428182 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1335. Min Range: -9.1335
Max Act: 8.8835. Min Act: -0.1700
Data Index: 4124051 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1335. Min Range: -9.1335
Max Act: 8.0710. Min Act: -0.1700
Data Index: 5970645 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1335. Min Range: -9.1335
Max Act: 8.0710. Min Act: -0.1700
Data Index: 5883706 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1335. Min Range: -9.1335
Max Act: 8.0085. Min Act: -0.1700
Data Index: 1754920 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1335. Min Range: -9.1335
Max Act: 8.0085. Min Act: -0.1700
Data Index: 538645 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1335. Min Range: -9.1335
Max Act: 8.0085. Min Act: -0.1700
Data Index: 2872028 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.9460. Min Act: -0.1700
Data Index: 7664214 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.8210. Min Act: -0.1700
Data Index: 6420841 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.7585. Min Act: -0.1700
Data Index: 7581568 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.7585. Min Act: -0.1700
Data Index: 1995493 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.8210. Min Act: -0.1700
Data Index: 854258 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.7585. Min Act: -0.1700
Data Index: 7308436 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.7585. Min Act: -0.1700
Data Index: 3530239 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.6960. Min Act: -0.1700
Data Index: 1243242 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.6960. Min Act: -0.1700
Data Index: 6561548 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.6022. Min Act: -0.1700
Data Index: 4391261 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.6335. Min Act: -0.1700
Data Index: 3628250 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.6022. Min Act: -0.1700
Data Index: 2197756 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1335. Min Range: -9.1335
Max Act: 7.5710. Min Act: -0.1700
Data Index: 6400484 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19