Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.8536. Min Act: -0.1700
Data Index: 18854 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.8223. Min Act: -0.1700
Data Index: 3978224 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.7911. Min Act: -0.1700
Data Index: 2384305 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.7286. Min Act: -0.1700
Data Index: 8316656 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.6661. Min Act: -0.1700
Data Index: 3824412 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.6036. Min Act: -0.1700
Data Index: 1651598 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.6036. Min Act: -0.1700
Data Index: 2082933 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.5411. Min Act: -0.1700
Data Index: 7161078 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.4786. Min Act: -0.1700
Data Index: 72530 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.4786. Min Act: -0.1700
Data Index: 6677294 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.4161. Min Act: -0.1700
Data Index: 7199591 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.4161. Min Act: -0.1700
Data Index: 2304270 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.4161. Min Act: -0.1700
Data Index: 11334 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.4161. Min Act: -0.1700
Data Index: 4674874 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.3848. Min Act: -0.1700
Data Index: 8470436 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.3848. Min Act: -0.1700
Data Index: 8303687 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.3848. Min Act: -0.1700
Data Index: 4131856 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.3848. Min Act: -0.1700
Data Index: 2749164 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.3848. Min Act: -0.1700
Data Index: 2034815 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8536. Min Range: -5.8536
Max Act: 5.3536. Min Act: -0.1700
Data Index: 2895399 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19