Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 375 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.6988. Min Act: -0.1700
Data Index: 7617417 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.3863. Min Act: -0.1700
Data Index: 1948916 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.3863. Min Act: -0.1700
Data Index: 169275 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.1363. Min Act: -0.1700
Data Index: 5303749 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.1988. Min Act: -0.1700
Data Index: 1272002 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.1363. Min Act: -0.1700
Data Index: 8513172 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.0738. Min Act: -0.1700
Data Index: 1538741 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.0113. Min Act: -0.1700
Data Index: 3021310 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.0113. Min Act: -0.1700
Data Index: 6795850 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.0113. Min Act: -0.1700
Data Index: 7875070 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.0113. Min Act: -0.1700
Data Index: 8447511 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6988. Min Range: -8.6988
Max Act: 8.0113. Min Act: -0.1700
Data Index: 1720250 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.9488. Min Act: -0.1700
Data Index: 2881542 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.9488. Min Act: -0.1700
Data Index: 4970978 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.9488. Min Act: -0.1700
Data Index: 5343334 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.8863. Min Act: -0.1700
Data Index: 4372329 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.8238. Min Act: -0.1700
Data Index: 2680679 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.7613. Min Act: -0.1700
Data Index: 3199560 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.8238. Min Act: -0.1700
Data Index: 2331733 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6988. Min Range: -8.6988
Max Act: 7.7613. Min Act: -0.1700
Data Index: 846276 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19