Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.2728. Min Act: -0.1700
Data Index: 1012421 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.2728. Min Act: -0.1700
Data Index: 7731972 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.2415. Min Act: -0.1700
Data Index: 1755170 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.2415. Min Act: -0.1700
Data Index: 4614953 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.2103. Min Act: -0.1700
Data Index: 2214840 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.1790. Min Act: -0.1700
Data Index: 8755283 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.1477. Min Act: -0.1700
Data Index: 6964849 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.1477. Min Act: -0.1700
Data Index: 229797 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.1477. Min Act: -0.1700
Data Index: 8760893 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.1165. Min Act: -0.1700
Data Index: 5573862 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0852. Min Act: -0.1700
Data Index: 2041838 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0852. Min Act: -0.1700
Data Index: 226332 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0852. Min Act: -0.1700
Data Index: 5929195 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0852. Min Act: -0.1700
Data Index: 4722660 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0852. Min Act: -0.1700
Data Index: 743992 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0540. Min Act: -0.1700
Data Index: 5199696 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0540. Min Act: -0.1700
Data Index: 5573863 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0540. Min Act: -0.1700
Data Index: 1648373 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0540. Min Act: -0.1700
Data Index: 1010644 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2728. Min Range: -4.2728
Max Act: 4.0227. Min Act: -0.1700
Data Index: 4614956 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19