Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.8461. Min Act: -0.1700
Data Index: 2042570 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.7211. Min Act: -0.1700
Data Index: 3139642 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.6586. Min Act: -0.1700
Data Index: 8143224 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.5961. Min Act: -0.1700
Data Index: 5537702 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.5336. Min Act: -0.1700
Data Index: 5537828 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.3461. Min Act: -0.1700
Data Index: 2279070 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.3461. Min Act: -0.1700
Data Index: 1970247 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.3461. Min Act: -0.1700
Data Index: 6002866 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.3461. Min Act: -0.1700
Data Index: 1764011 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.3461. Min Act: -0.1700
Data Index: 5764852 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.3461. Min Act: -0.1700
Data Index: 5459466 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.3461. Min Act: -0.1700
Data Index: 390891 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2836. Min Act: -0.1700
Data Index: 856479 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2836. Min Act: -0.1700
Data Index: 3472972 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2836. Min Act: -0.1700
Data Index: 6315668 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2836. Min Act: -0.1700
Data Index: 7125190 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2836. Min Act: -0.1700
Data Index: 7376463 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2836. Min Act: -0.1700
Data Index: 4875403 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2211. Min Act: -0.1700
Data Index: 2620243 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8461. Min Range: -8.8461
Max Act: 8.2211. Min Act: -0.1700
Data Index: 2782954 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19