Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0060. Min Range: -10.0060
Max Act: 10.0060. Min Act: -0.1700
Data Index: 1834373 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0060. Min Range: -10.0060
Max Act: 10.0060. Min Act: -0.1700
Data Index: 2120937 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.7560. Min Act: -0.1700
Data Index: 1239300 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.7560. Min Act: -0.1700
Data Index: 175494 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.6310. Min Act: -0.1700
Data Index: 6416924 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.6310. Min Act: -0.1700
Data Index: 7661003 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.5685. Min Act: -0.1700
Data Index: 7600046 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.5685. Min Act: -0.1700
Data Index: 2226634 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.5060. Min Act: -0.1700
Data Index: 1523635 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.5685. Min Act: -0.1700
Data Index: 4977675 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.4435. Min Act: -0.1700
Data Index: 8094052 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.4435. Min Act: -0.1700
Data Index: 1791486 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.3810. Min Act: -0.1700
Data Index: 2204954 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.3185. Min Act: -0.1700
Data Index: 8659177 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.2560. Min Act: -0.1700
Data Index: 4209338 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.2560. Min Act: -0.1700
Data Index: 8066929 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.2560. Min Act: -0.1700
Data Index: 8320760 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.1935. Min Act: -0.1700
Data Index: 2194563 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.1935. Min Act: -0.1700
Data Index: 834544 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0060. Min Range: -10.0060
Max Act: 9.1935. Min Act: -0.1700
Data Index: 6147314 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19