Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 6079764 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.8836. Min Act: -0.1700
Data Index: 2646313 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.8680. Min Act: -0.1700
Data Index: 6289470 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.8367. Min Act: -0.1700
Data Index: 1656020 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7898. Min Act: -0.1700
Data Index: 832993 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7898. Min Act: -0.1700
Data Index: 5270563 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7898. Min Act: -0.1700
Data Index: 1094703 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7742. Min Act: -0.1700
Data Index: 3350041 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7585. Min Act: -0.1700
Data Index: 1094704 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7429. Min Act: -0.1700
Data Index: 8002211 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7429. Min Act: -0.1700
Data Index: 7753646 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7429. Min Act: -0.1700
Data Index: 5320766 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7429. Min Act: -0.1700
Data Index: 6330508 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7429. Min Act: -0.1700
Data Index: 6978439 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7273. Min Act: -0.1700
Data Index: 1461234 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7116. Min Act: -0.1700
Data Index: 2291330 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7116. Min Act: -0.1700
Data Index: 3901524 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.6960. Min Act: -0.1700
Data Index: 257931 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.6960. Min Act: -0.1700
Data Index: 7326617 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.7116. Min Act: -0.1700
Data Index: 6564060 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19