Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4560 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.1710. Min Act: -0.1700
Data Index: 3476211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.1398. Min Act: -0.1700
Data Index: 1886521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.1085. Min Act: -0.1700
Data Index: 6524426 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.1398. Min Act: -0.1699
Data Index: 5481332 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.1085. Min Act: -0.1699
Data Index: 2251317 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0773. Min Act: -0.1700
Data Index: 7605065 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0460. Min Act: -0.1700
Data Index: 6356441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1697
Data Index: 3698944 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0460. Min Act: -0.1700
Data Index: 3868784 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0460. Min Act: -0.1698
Data Index: 8658699 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0460. Min Act: -0.1700
Data Index: 3730994 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1700
Data Index: 4365680 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1004706 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9835. Min Act: -0.1700
Data Index: 4119097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1009584 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1700
Data Index: 3803543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1700
Data Index: 6822040 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1090025 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1886490 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9835. Min Act: -0.1700
Data Index: 2333620 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19