Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0818. Min Range: -5.0818
Max Act: 5.0818. Min Act: -0.1700
Data Index: 3359311 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0818. Min Range: -5.0818
Max Act: 5.0818. Min Act: -0.1700
Data Index: 829057 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.8943. Min Act: -0.1700
Data Index: 3359304 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.8943. Min Act: -0.1700
Data Index: 5152418 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.8630. Min Act: -0.1700
Data Index: 6091244 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.8630. Min Act: -0.1700
Data Index: 829056 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.8318. Min Act: -0.1700
Data Index: 893771 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.8318. Min Act: -0.1700
Data Index: 8296121 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7693. Min Act: -0.1700
Data Index: 5664652 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7693. Min Act: -0.1700
Data Index: 8516230 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.8005. Min Act: -0.1700
Data Index: 5850557 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7380. Min Act: -0.1700
Data Index: 733555 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7693. Min Act: -0.1700
Data Index: 7383505 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7380. Min Act: -0.1700
Data Index: 3359297 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7068. Min Act: -0.1700
Data Index: 3090969 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7068. Min Act: -0.1700
Data Index: 3359308 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7380. Min Act: -0.1700
Data Index: 3038168 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7068. Min Act: -0.1700
Data Index: 7455384 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.7068. Min Act: -0.1700
Data Index: 1280278 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0818. Min Range: -5.0818
Max Act: 4.6755. Min Act: -0.1700
Data Index: 840570 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19