Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 312 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5732. Min Range: -9.5732
Max Act: 9.5732. Min Act: -0.1700
Data Index: 5729778 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.9482. Min Act: -0.1700
Data Index: 7984217 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.8857. Min Act: -0.1700
Data Index: 4613707 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.8232. Min Act: -0.1700
Data Index: 6144244 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.8232. Min Act: -0.1700
Data Index: 7556370 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.7607. Min Act: -0.1700
Data Index: 6050536 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.6982. Min Act: -0.1700
Data Index: 1772723 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.6357. Min Act: -0.1700
Data Index: 6744052 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 1992620 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.6357. Min Act: -0.1700
Data Index: 6758195 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 8794882 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 7386964 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 6665372 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5107. Min Act: -0.1700
Data Index: 4307184 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 2455855 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.4482. Min Act: -0.1700
Data Index: 8508284 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5107. Min Act: -0.1700
Data Index: 4258890 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.5107. Min Act: -0.1700
Data Index: 1050101 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.4482. Min Act: -0.1700
Data Index: 6416545 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5732. Min Range: -9.5732
Max Act: 8.4482. Min Act: -0.1700
Data Index: 3509940 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19