Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4579 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.6870. Min Act: -0.1700
Data Index: 4292559 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.5933. Min Act: -0.1700
Data Index: 318361 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.5620. Min Act: -0.1700
Data Index: 4411806 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.4058. Min Act: -0.1700
Data Index: 6553832 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.4058. Min Act: -0.1700
Data Index: 8776315 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.4058. Min Act: -0.1700
Data Index: 1849359 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.4058. Min Act: -0.1700
Data Index: 2555092 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.3120. Min Act: -0.1700
Data Index: 4873742 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.3120. Min Act: -0.1700
Data Index: 7536456 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.3120. Min Act: -0.1700
Data Index: 3311434 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.3120. Min Act: -0.1700
Data Index: 6430902 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2808. Min Act: -0.1700
Data Index: 8047794 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2808. Min Act: -0.1700
Data Index: 6637581 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2183. Min Act: -0.1700
Data Index: 8397194 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3921295 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2495. Min Act: -0.1700
Data Index: 1663964 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3796130 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2183. Min Act: -0.1700
Data Index: 7717171 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2183. Min Act: -0.1700
Data Index: 179304 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6870. Min Range: -6.6870
Max Act: 6.2183. Min Act: -0.1700
Data Index: 540207 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19