Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.2641. Min Act: -0.1700
Data Index: 312947 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.2641. Min Act: -0.1700
Data Index: 415818 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.2476. Min Act: -0.1700
Data Index: 5495205 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.2476. Min Act: -0.1700
Data Index: 5797673 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.2311. Min Act: -0.1700
Data Index: 7248848 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.2145. Min Act: -0.1700
Data Index: 8011519 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.2145. Min Act: -0.1700
Data Index: 1023096 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1979. Min Act: -0.1700
Data Index: 2603483 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1979. Min Act: -0.1700
Data Index: 3711211 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1979. Min Act: -0.1700
Data Index: 8086983 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1647. Min Act: -0.1700
Data Index: 2461454 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1480. Min Act: -0.1700
Data Index: 8267321 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1647. Min Act: -0.1700
Data Index: 1826957 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1647. Min Act: -0.1700
Data Index: 7124440 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1647. Min Act: -0.1700
Data Index: 4845456 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1480. Min Act: -0.1700
Data Index: 4771259 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1480. Min Act: -0.1700
Data Index: 8512045 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1480. Min Act: -0.1700
Data Index: 6182871 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1480. Min Act: -0.1700
Data Index: 6229444 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2641. Min Range: -2.2641
Max Act: 2.1313. Min Act: -0.1700
Data Index: 5801250 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19