Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.6668. Min Act: -0.1700
Data Index: 6196935 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.3855. Min Act: -0.1700
Data Index: 2976622 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.3230. Min Act: -0.1700
Data Index: 755345 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.3230. Min Act: -0.1700
Data Index: 1033734 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.2605. Min Act: -0.1700
Data Index: 4301898 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.2293. Min Act: -0.1700
Data Index: 4974016 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1980. Min Act: -0.1700
Data Index: 248528 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1668. Min Act: -0.1700
Data Index: 6120136 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1668. Min Act: -0.1700
Data Index: 405902 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1668. Min Act: -0.1700
Data Index: 1599013 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1668. Min Act: -0.1700
Data Index: 248523 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1355. Min Act: -0.1700
Data Index: 128011 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1043. Min Act: -0.1700
Data Index: 1951657 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1043. Min Act: -0.1700
Data Index: 8241036 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.0730. Min Act: -0.1700
Data Index: 2507455 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.1043. Min Act: -0.1700
Data Index: 3990207 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.0730. Min Act: -0.1700
Data Index: 302297 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.0418. Min Act: -0.1700
Data Index: 248529 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.0730. Min Act: -0.1700
Data Index: 6350556 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6668. Min Range: -5.6668
Max Act: 5.0418. Min Act: -0.1700
Data Index: 3883215 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19