Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2360 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.7532. Min Act: -0.1700
Data Index: 4955823 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.6282. Min Act: -0.1700
Data Index: 8390673 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.5657. Min Act: -0.1700
Data Index: 2820084 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.5970. Min Act: -0.1700
Data Index: 4079918 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.5970. Min Act: -0.1700
Data Index: 6247262 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.5345. Min Act: -0.1700
Data Index: 4943913 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.5032. Min Act: -0.1700
Data Index: 2158323 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.4720. Min Act: -0.1700
Data Index: 2693783 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.1907. Min Act: -0.1700
Data Index: 2783860 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.1907. Min Act: -0.1700
Data Index: 360447 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.1907. Min Act: -0.1700
Data Index: 4376156 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.1282. Min Act: -0.1700
Data Index: 2783865 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.0970. Min Act: -0.1700
Data Index: 1672879 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.0970. Min Act: -0.1700
Data Index: 1506897 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.0657. Min Act: -0.1700
Data Index: 8677388 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.0970. Min Act: -0.1700
Data Index: 2119000 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.1282. Min Act: -0.1700
Data Index: 1985449 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.0970. Min Act: -0.1700
Data Index: 8590905 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.0657. Min Act: -0.1700
Data Index: 8380799 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7532. Min Range: -7.7532
Max Act: 7.0657. Min Act: -0.1700
Data Index: 7344991 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19