Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4529. Min Range: -7.4529
Max Act: 7.4529. Min Act: -0.1700
Data Index: 8199103 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4529. Min Range: -7.4529
Max Act: 7.2029. Min Act: -0.1700
Data Index: 4131734 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4529. Min Range: -7.4529
Max Act: 7.1404. Min Act: -0.1700
Data Index: 7757292 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4529. Min Range: -7.4529
Max Act: 7.0467. Min Act: -0.1700
Data Index: 1332476 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4529. Min Range: -7.4529
Max Act: 7.0154. Min Act: -0.1700
Data Index: 6908450 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.9842. Min Act: -0.1700
Data Index: 3389367 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.9842. Min Act: -0.1700
Data Index: 7362897 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.9217. Min Act: -0.1700
Data Index: 1171546 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8904. Min Act: -0.1700
Data Index: 6140171 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8904. Min Act: -0.1700
Data Index: 8585191 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8904. Min Act: -0.1700
Data Index: 1753631 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8904. Min Act: -0.1700
Data Index: 5168992 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8592. Min Act: -0.1700
Data Index: 4763705 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8279. Min Act: -0.1700
Data Index: 292993 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8279. Min Act: -0.1700
Data Index: 737507 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.7967. Min Act: -0.1700
Data Index: 1005818 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.7967. Min Act: -0.1700
Data Index: 417271 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.7654. Min Act: -0.1700
Data Index: 2423788 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.8279. Min Act: -0.1700
Data Index: 8577749 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4529. Min Range: -7.4529
Max Act: 6.7654. Min Act: -0.1700
Data Index: 576705 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19