Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2146 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.8525. Min Act: -0.1700
Data Index: 473745 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.8213. Min Act: -0.1700
Data Index: 7540527 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.7275. Min Act: -0.1700
Data Index: 667513 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6963. Min Act: -0.1700
Data Index: 5216142 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6650. Min Act: -0.1700
Data Index: 7866538 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6338. Min Act: -0.1700
Data Index: 2321467 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6650. Min Act: -0.1700
Data Index: 4487805 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6650. Min Act: -0.1700
Data Index: 4343491 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6650. Min Act: -0.1700
Data Index: 521903 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6650. Min Act: -0.1700
Data Index: 4389390 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6338. Min Act: -0.1700
Data Index: 5824391 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6338. Min Act: -0.1700
Data Index: 8760403 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6025. Min Act: -0.1700
Data Index: 432517 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6025. Min Act: -0.1700
Data Index: 7814928 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6025. Min Act: -0.1700
Data Index: 1536402 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6025. Min Act: -0.1700
Data Index: 2564053 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.6025. Min Act: -0.1700
Data Index: 8222359 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7636321 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.5713. Min Act: -0.1700
Data Index: 1864333 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8525. Min Range: -5.8525
Max Act: 5.5713. Min Act: -0.1700
Data Index: 2628735 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19