Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.9269. Min Act: -0.1700
Data Index: 6549403 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.8019. Min Act: -0.1700
Data Index: 7369760 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.6769. Min Act: -0.1700
Data Index: 4559527 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.6769. Min Act: -0.1700
Data Index: 3040598 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.6456. Min Act: -0.1700
Data Index: 1983686 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.6456. Min Act: -0.1700
Data Index: 260916 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.6144. Min Act: -0.1700
Data Index: 3468499 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.5519. Min Act: -0.1700
Data Index: 1611182 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.5831. Min Act: -0.1700
Data Index: 3760220 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.5831. Min Act: -0.1700
Data Index: 1565602 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.5206. Min Act: -0.1700
Data Index: 514514 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.4581. Min Act: -0.1700
Data Index: 7663845 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.4581. Min Act: -0.1700
Data Index: 7885439 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.4581. Min Act: -0.1700
Data Index: 5088427 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.4269. Min Act: -0.1700
Data Index: 4029853 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.3956. Min Act: -0.1700
Data Index: 3432641 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.3956. Min Act: -0.1700
Data Index: 3838322 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.3331. Min Act: -0.1700
Data Index: 4860210 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.3644. Min Act: -0.1700
Data Index: 7294232 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9269. Min Range: -4.9269
Max Act: 4.3644. Min Act: -0.1700
Data Index: 7456716 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19