Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0571. Min Act: -0.1700
Data Index: 7839768 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 7707172 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 618980 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 628145 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0571. Min Range: -5.0571
Max Act: 4.9946. Min Act: -0.1700
Data Index: 1670942 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 3543271 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 4853162 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 1105261 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 4828741 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 134335 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 4335556 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 3960010 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 3360110 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 882992 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 743189 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 3812717 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 304990 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0571. Min Range: -5.0571
Max Act: 4.9946. Min Act: -0.1700
Data Index: 3102696 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 735463 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0571. Min Range: -5.0571
Max Act: 5.0259. Min Act: -0.1700
Data Index: 617742 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19