Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1124 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6335. Min Range: -6.6335
Max Act: 6.6335. Min Act: -0.1700
Data Index: 6928222 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6335. Min Range: -6.6335
Max Act: 6.5710. Min Act: -0.1700
Data Index: 4614823 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6335. Min Range: -6.6335
Max Act: 6.2585. Min Act: -0.1700
Data Index: 4382405 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6335. Min Range: -6.6335
Max Act: 6.1647. Min Act: -0.1700
Data Index: 6453081 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6335. Min Range: -6.6335
Max Act: 6.0710. Min Act: -0.1700
Data Index: 5971045 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6335. Min Range: -6.6335
Max Act: 6.0397. Min Act: -0.1700
Data Index: 2763352 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6335. Min Range: -6.6335
Max Act: 6.0085. Min Act: -0.1700
Data Index: 4684990 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.9460. Min Act: -0.1700
Data Index: 5123461 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.9147. Min Act: -0.1700
Data Index: 3269091 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 4565023 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 6246894 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 705505 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.8522. Min Act: -0.1700
Data Index: 7525842 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.8522. Min Act: -0.1700
Data Index: 4566406 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 5097736 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.8210. Min Act: -0.1700
Data Index: 4072186 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.7897. Min Act: -0.1700
Data Index: 7078140 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.7272. Min Act: -0.1700
Data Index: 4512363 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.6960. Min Act: -0.1700
Data Index: 805342 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6335. Min Range: -6.6335
Max Act: 5.6960. Min Act: -0.1700
Data Index: 2080945 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19