Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4492 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0930. Min Range: -4.0930
Max Act: 4.0930. Min Act: -0.1700
Data Index: 1233798 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0930. Min Range: -4.0930
Max Act: 4.0305. Min Act: -0.1700
Data Index: 3008717 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0930. Min Range: -4.0930
Max Act: 4.0305. Min Act: -0.1700
Data Index: 8390340 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9992. Min Act: -0.1700
Data Index: 4305142 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9992. Min Act: -0.1700
Data Index: 6951067 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9992. Min Act: -0.1700
Data Index: 5293254 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9992. Min Act: -0.1700
Data Index: 2680394 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9680. Min Act: -0.1700
Data Index: 7414524 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9992. Min Act: -0.1700
Data Index: 7259832 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9680. Min Act: -0.1700
Data Index: 6489900 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9367. Min Act: -0.1700
Data Index: 1165461 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9367. Min Act: -0.1700
Data Index: 5406144 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9055. Min Act: -0.1700
Data Index: 5084609 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9055. Min Act: -0.1700
Data Index: 483841 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9055. Min Act: -0.1700
Data Index: 5524213 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9367. Min Act: -0.1700
Data Index: 1685413 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9367. Min Act: -0.1700
Data Index: 2084620 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.9055. Min Act: -0.1700
Data Index: 3462546 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.8742. Min Act: -0.1700
Data Index: 1247071 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0930. Min Range: -4.0930
Max Act: 3.8742. Min Act: -0.1700
Data Index: 1314502 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19