Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2732 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.7537. Min Act: -0.1700
Data Index: 6239861 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.5037. Min Act: -0.1700
Data Index: 1773056 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4724. Min Act: -0.1700
Data Index: 3046458 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4412. Min Act: -0.1700
Data Index: 4589872 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4412. Min Act: -0.1700
Data Index: 3782216 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.4412. Min Act: -0.1700
Data Index: 6578384 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3787. Min Act: -0.1700
Data Index: 1184608 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3787. Min Act: -0.1700
Data Index: 2736165 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.3474. Min Act: -0.1700
Data Index: 7068204 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.2224. Min Act: -0.1700
Data Index: 5366316 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.1599. Min Act: -0.1700
Data Index: 8308132 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.1599. Min Act: -0.1700
Data Index: 3313647 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.1287. Min Act: -0.1700
Data Index: 853556 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.1287. Min Act: -0.1700
Data Index: 3038337 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.0974. Min Act: -0.1700
Data Index: 1751420 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.1287. Min Act: -0.1700
Data Index: 1299590 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.0662. Min Act: -0.1700
Data Index: 1040449 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.0662. Min Act: -0.1700
Data Index: 1664731 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.0662. Min Act: -0.1700
Data Index: 5033221 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7537. Min Range: -6.7537
Max Act: 6.0662. Min Act: -0.1700
Data Index: 4080669 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19