Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2411 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4918. Min Range: -9.4918
Max Act: 9.4918. Min Act: -0.1700
Data Index: 6369994 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4918. Min Range: -9.4918
Max Act: 9.3668. Min Act: -0.1700
Data Index: 8498601 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4918. Min Range: -9.4918
Max Act: 9.1793. Min Act: -0.1700
Data Index: 739672 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4918. Min Range: -9.4918
Max Act: 9.0543. Min Act: -0.1700
Data Index: 7387235 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4918. Min Range: -9.4918
Max Act: 9.0543. Min Act: -0.1700
Data Index: 1435975 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.9918. Min Act: -0.1700
Data Index: 4714804 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.9293. Min Act: -0.1700
Data Index: 8402745 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.9293. Min Act: -0.1700
Data Index: 8774546 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.9293. Min Act: -0.1700
Data Index: 8795462 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.8668. Min Act: -0.1700
Data Index: 2393472 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.8043. Min Act: -0.1700
Data Index: 112031 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.8043. Min Act: -0.1700
Data Index: 3259402 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.7418. Min Act: -0.1700
Data Index: 5826636 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.7418. Min Act: -0.1700
Data Index: 6873629 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.8043. Min Act: -0.1700
Data Index: 2904931 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.6793. Min Act: -0.1700
Data Index: 3536347 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.6168. Min Act: -0.1700
Data Index: 3884838 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.6793. Min Act: -0.1700
Data Index: 6898846 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.6168. Min Act: -0.1700
Data Index: 1320188 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4918. Min Range: -9.4918
Max Act: 8.6168. Min Act: -0.1700
Data Index: 1919881 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19