Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 340 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.6077. Min Act: -0.1700
Data Index: 6428491 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.5452. Min Act: -0.1700
Data Index: 1381751 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.5139. Min Act: -0.1700
Data Index: 7031793 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.4827. Min Act: -0.1700
Data Index: 116620 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.4514. Min Act: -0.1700
Data Index: 5076511 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2639. Min Act: -0.1700
Data Index: 1313283 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2952. Min Act: -0.1700
Data Index: 7545255 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 6537558 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 4062050 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 2022107 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 6582250 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2014. Min Act: -0.1700
Data Index: 2510082 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1702. Min Act: -0.1700
Data Index: 7811702 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1702. Min Act: -0.1700
Data Index: 3769749 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1702. Min Act: -0.1700
Data Index: 5076513 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1702. Min Act: -0.1700
Data Index: 8629630 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1702. Min Act: -0.1700
Data Index: 1225493 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1389. Min Act: -0.1700
Data Index: 8019585 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1389. Min Act: -0.1700
Data Index: 3921323 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1389. Min Act: -0.1700
Data Index: 7303016 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19