Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4711 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.7967. Min Act: -0.1700
Data Index: 8554887 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.4217. Min Act: -0.1700
Data Index: 2324019 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.4529. Min Act: -0.1700
Data Index: 8281595 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.3904. Min Act: -0.1700
Data Index: 5802538 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.3904. Min Act: -0.1700
Data Index: 2770634 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.3592. Min Act: -0.1700
Data Index: 7183986 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.3592. Min Act: -0.1700
Data Index: 7493395 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2967. Min Act: -0.1700
Data Index: 1315315 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.3279. Min Act: -0.1700
Data Index: 2670877 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2967. Min Act: -0.1700
Data Index: 3077126 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2342. Min Act: -0.1700
Data Index: 8817941 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2654. Min Act: -0.1700
Data Index: 4678122 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2654. Min Act: -0.1700
Data Index: 3928480 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2654. Min Act: -0.1700
Data Index: 1762213 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2029. Min Act: -0.1700
Data Index: 503874 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2029. Min Act: -0.1699
Data Index: 1921470 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.1717. Min Act: -0.1700
Data Index: 8535979 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2029. Min Act: -0.1700
Data Index: 2452724 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2029. Min Act: -0.1700
Data Index: 5376822 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7967. Min Range: -5.7967
Max Act: 5.2029. Min Act: -0.1700
Data Index: 2452993 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19