Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2297 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.9412. Min Act: -0.1700
Data Index: 3207199 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8901. Min Act: -0.1700
Data Index: 4776650 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8901. Min Act: -0.1700
Data Index: 3041155 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8987. Min Act: -0.1700
Data Index: 7536237 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8731. Min Act: -0.1700
Data Index: 1532471 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8816. Min Act: -0.1700
Data Index: 6573644 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8645. Min Act: -0.1700
Data Index: 5203114 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8560. Min Act: -0.1700
Data Index: 4608933 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8560. Min Act: -0.1700
Data Index: 3523375 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8645. Min Act: -0.1700
Data Index: 4563319 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8645. Min Act: -0.1700
Data Index: 8186237 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8645. Min Act: -0.1700
Data Index: 832162 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8474. Min Act: -0.1700
Data Index: 6932894 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8388. Min Act: -0.1700
Data Index: 5473997 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8388. Min Act: -0.1699
Data Index: 5886809 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8388. Min Act: -0.1700
Data Index: 8384233 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8474. Min Act: -0.1700
Data Index: 6356136 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8302. Min Act: -0.1700
Data Index: 1217624 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8474. Min Act: -0.1700
Data Index: 3468657 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9412. Min Range: -1.9412
Max Act: 1.8388. Min Act: -0.1700
Data Index: 4649695 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19