Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 545 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.5049. Min Act: -0.1700
Data Index: 2413224 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.4074. Min Act: -0.1700
Data Index: 4006805 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.4074. Min Act: -0.1700
Data Index: 8460046 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.4074. Min Act: -0.1700
Data Index: 6451484 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.4237. Min Act: -0.1700
Data Index: 1412470 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.4074. Min Act: -0.1700
Data Index: 2658321 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3911. Min Act: -0.1700
Data Index: 1237655 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3748. Min Act: -0.1700
Data Index: 7597505 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3420. Min Act: -0.1700
Data Index: 639057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3256. Min Act: -0.1700
Data Index: 933235 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3420. Min Act: -0.1700
Data Index: 468167 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3092. Min Act: -0.1700
Data Index: 5740619 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3092. Min Act: -0.1700
Data Index: 131040 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.2927. Min Act: -0.1700
Data Index: 6955750 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3092. Min Act: -0.1700
Data Index: 2093167 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.2927. Min Act: -0.1700
Data Index: 1375213 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.2927. Min Act: -0.1700
Data Index: 8176152 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3092. Min Act: -0.1700
Data Index: 449514 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.3092. Min Act: -0.1700
Data Index: 91133 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5049. Min Range: -2.5049
Max Act: 2.2927. Min Act: -0.1700
Data Index: 6059935 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19