Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.3599. Min Act: -0.1700
Data Index: 7822868 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2661. Min Act: -0.1700
Data Index: 6147015 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2974. Min Act: -0.1700
Data Index: 8624013 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2661. Min Act: -0.1700
Data Index: 943166 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2661. Min Act: -0.1700
Data Index: 1322545 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2349. Min Act: -0.1700
Data Index: 6951452 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2036. Min Act: -0.1700
Data Index: 7627992 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1411. Min Act: -0.1700
Data Index: 3442442 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1411. Min Act: -0.1700
Data Index: 3803068 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1099. Min Act: -0.1700
Data Index: 5695504 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.0786. Min Act: -0.1700
Data Index: 5256155 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.0474. Min Act: -0.1700
Data Index: 3118782 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.9536. Min Act: -0.1700
Data Index: 6855671 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.9849. Min Act: -0.1700
Data Index: 2767821 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.9224. Min Act: -0.1700
Data Index: 595264 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.9849. Min Act: -0.1700
Data Index: 6121885 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.9536. Min Act: -0.1700
Data Index: 7039451 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.9536. Min Act: -0.1700
Data Index: 4648109 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.8911. Min Act: -0.1700
Data Index: 4174932 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3599. Min Range: -5.3599
Max Act: 4.9224. Min Act: -0.1700
Data Index: 7620913 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19