Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.5542. Min Act: -0.1700
Data Index: 5132786 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.3667. Min Act: -0.1700
Data Index: 3236644 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.3355. Min Act: -0.1700
Data Index: 5377032 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.2730. Min Act: -0.1700
Data Index: 4334092 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.2730. Min Act: -0.1700
Data Index: 7538846 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.2417. Min Act: -0.1700
Data Index: 6738474 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.2417. Min Act: -0.1700
Data Index: 2242700 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.2105. Min Act: -0.1700
Data Index: 423665 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.2105. Min Act: -0.1700
Data Index: 2690960 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1792. Min Act: -0.1700
Data Index: 6927356 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1792. Min Act: -0.1700
Data Index: 990834 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1480. Min Act: -0.1700
Data Index: 778677 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1480. Min Act: -0.1700
Data Index: 6171482 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1480. Min Act: -0.1700
Data Index: 6065184 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1480. Min Act: -0.1700
Data Index: 1875644 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1167. Min Act: -0.1700
Data Index: 7295295 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1167. Min Act: -0.1700
Data Index: 7985464 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1969546 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1570001 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5542. Min Range: -5.5542
Max Act: 5.0855. Min Act: -0.1700
Data Index: 2794278 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19