Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.3083. Min Act: -0.1700
Data Index: 3389493 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.3240. Min Act: -0.1700
Data Index: 4344624 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2926. Min Act: -0.1700
Data Index: 7489530 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2612. Min Act: -0.1700
Data Index: 2578141 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2612. Min Act: -0.1700
Data Index: 4916675 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2455. Min Act: -0.1700
Data Index: 2812665 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2455. Min Act: -0.1700
Data Index: 2671722 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2455. Min Act: -0.1700
Data Index: 6527604 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2455. Min Act: -0.1700
Data Index: 7809691 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2455. Min Act: -0.1700
Data Index: 1974971 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2298. Min Act: -0.1700
Data Index: 5786380 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1984. Min Act: -0.1700
Data Index: 5067172 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1984. Min Act: -0.1700
Data Index: 8830414 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1984. Min Act: -0.1700
Data Index: 1382765 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.2141. Min Act: -0.1700
Data Index: 8585258 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1984. Min Act: -0.1700
Data Index: 4297906 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1984. Min Act: -0.1700
Data Index: 7651115 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1826. Min Act: -0.1700
Data Index: 3868407 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1669. Min Act: -0.1700
Data Index: 51874 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3240. Min Range: -3.3240
Max Act: 3.1669. Min Act: -0.1700
Data Index: 4084251 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19