Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5020 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0321. Min Range: -7.0321
Max Act: 7.0321. Min Act: -0.1700
Data Index: 5932639 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0321. Min Range: -7.0321
Max Act: 7.0009. Min Act: -0.1700
Data Index: 630328 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.9071. Min Act: -0.1700
Data Index: 3477167 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.8759. Min Act: -0.1700
Data Index: 8233220 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.7196. Min Act: -0.1700
Data Index: 6567374 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.7196. Min Act: -0.1700
Data Index: 516903 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.7196. Min Act: -0.1700
Data Index: 1553415 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.6571. Min Act: -0.1700
Data Index: 4636586 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.5634. Min Act: -0.1700
Data Index: 3883937 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.5946. Min Act: -0.1700
Data Index: 1811967 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.5946. Min Act: -0.1700
Data Index: 6055830 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.5634. Min Act: -0.1700
Data Index: 6269506 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.5321. Min Act: -0.1700
Data Index: 1607564 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.5009. Min Act: -0.1700
Data Index: 6182207 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.5009. Min Act: -0.1700
Data Index: 1882167 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.4696. Min Act: -0.1700
Data Index: 7109104 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.4384. Min Act: -0.1700
Data Index: 3127345 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.4696. Min Act: -0.1700
Data Index: 1337286 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.4384. Min Act: -0.1700
Data Index: 1398496 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0321. Min Range: -7.0321
Max Act: 6.4696. Min Act: -0.1700
Data Index: 6197681 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19