Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.9736. Min Act: -0.1700
Data Index: 2771195 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.9424. Min Act: -0.1700
Data Index: 2944253 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.9424. Min Act: -0.1700
Data Index: 2453069 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.8799. Min Act: -0.1700
Data Index: 6298754 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.8486. Min Act: -0.1700
Data Index: 6866510 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.8174. Min Act: -0.1700
Data Index: 1304082 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.7549. Min Act: -0.1700
Data Index: 5437542 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.7236. Min Act: -0.1700
Data Index: 6343631 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.7236. Min Act: -0.1700
Data Index: 3363950 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6924. Min Act: -0.1700
Data Index: 5698737 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6924. Min Act: -0.1700
Data Index: 8753067 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6611. Min Act: -0.1700
Data Index: 1466463 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5986. Min Act: -0.1700
Data Index: 5325346 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5986. Min Act: -0.1700
Data Index: 941842 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.6299. Min Act: -0.1700
Data Index: 8769750 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5674. Min Act: -0.1700
Data Index: 1839928 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5361. Min Act: -0.1700
Data Index: 4175256 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5361. Min Act: -0.1700
Data Index: 8789326 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5361. Min Act: -0.1700
Data Index: 3287505 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9736. Min Range: -5.9736
Max Act: 5.5049. Min Act: -0.1700
Data Index: 6580101 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19