Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5708 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3286. Min Range: -8.3286
Max Act: 8.3286. Min Act: -0.1700
Data Index: 7487410 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.8911. Min Act: -0.1700
Data Index: 2163276 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.8286. Min Act: -0.1700
Data Index: 4165389 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.7036. Min Act: -0.1700
Data Index: 7085936 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.6724. Min Act: -0.1700
Data Index: 1490430 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.6411. Min Act: -0.1700
Data Index: 6953024 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.6724. Min Act: -0.1700
Data Index: 4074986 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.5786. Min Act: -0.1700
Data Index: 819622 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.5474. Min Act: -0.1700
Data Index: 5763350 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.5786. Min Act: -0.1700
Data Index: 2245391 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.4849. Min Act: -0.1700
Data Index: 3750457 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.4849. Min Act: -0.1700
Data Index: 4508394 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.3911. Min Act: -0.1700
Data Index: 3136405 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.4536. Min Act: -0.1700
Data Index: 5763355 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.4536. Min Act: -0.1700
Data Index: 1969573 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.3911. Min Act: -0.1700
Data Index: 3536690 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.3599. Min Act: -0.1700
Data Index: 5793667 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.3911. Min Act: -0.1700
Data Index: 1748281 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.3599. Min Act: -0.1700
Data Index: 1950188 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3286. Min Range: -8.3286
Max Act: 7.3599. Min Act: -0.1700
Data Index: 2208322 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19