Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.1799. Min Act: -0.1700
Data Index: 2434409 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.1174. Min Act: -0.1700
Data Index: 8267459 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0862. Min Act: -0.1700
Data Index: 6880995 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0862. Min Act: -0.1700
Data Index: 235928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0549. Min Act: -0.1700
Data Index: 7758547 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0549. Min Act: -0.1700
Data Index: 2006422 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0549. Min Act: -0.1700
Data Index: 400049 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 8258811 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1799. Min Range: -4.1799
Max Act: 3.9924. Min Act: -0.1700
Data Index: 452130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 58547 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 1707750 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0549. Min Act: -0.1700
Data Index: 3599987 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 7823239 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 3457983 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 304674 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 2163396 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 3520391 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 8700904 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1799. Min Range: -4.1799
Max Act: 4.0236. Min Act: -0.1700
Data Index: 5662544 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1799. Min Range: -4.1799
Max Act: 3.9924. Min Act: -0.1700
Data Index: 591240 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19