Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0234. Min Range: -7.0234
Max Act: 7.0234. Min Act: -0.1700
Data Index: 5385306 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.9921. Min Act: -0.1700
Data Index: 5061065 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.8046. Min Act: -0.1700
Data Index: 2150681 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.7734. Min Act: -0.1700
Data Index: 8090582 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.7421. Min Act: -0.1700
Data Index: 6928643 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.6796. Min Act: -0.1700
Data Index: 4644355 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.6484. Min Act: -0.1700
Data Index: 2343347 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.6171. Min Act: -0.1700
Data Index: 4636116 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.6484. Min Act: -0.1700
Data Index: 5887782 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.6484. Min Act: -0.1700
Data Index: 2674424 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.6171. Min Act: -0.1700
Data Index: 3307144 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.6171. Min Act: -0.1700
Data Index: 3307145 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5859. Min Act: -0.1700
Data Index: 585132 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5546. Min Act: -0.1700
Data Index: 6755272 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5546. Min Act: -0.1700
Data Index: 7089678 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5234. Min Act: -0.1700
Data Index: 172594 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5234. Min Act: -0.1700
Data Index: 7331245 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5546. Min Act: -0.1700
Data Index: 5236249 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5234. Min Act: -0.1700
Data Index: 1154425 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0234. Min Range: -7.0234
Max Act: 6.5234. Min Act: -0.1700
Data Index: 4486909 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19