Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4509 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.6312. Min Act: -0.1700
Data Index: 7489540 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.6151. Min Act: -0.1700
Data Index: 3643668 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.6151. Min Act: -0.1700
Data Index: 8522434 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.6151. Min Act: -0.1700
Data Index: 8291352 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 3698959 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 6521399 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 7772344 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 285086 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 4076895 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 3916709 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 1693447 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5668. Min Act: -0.1700
Data Index: 3470587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5668. Min Act: -0.1700
Data Index: 1313892 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5668. Min Act: -0.1700
Data Index: 5544183 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5829. Min Act: -0.1700
Data Index: 2104377 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5668. Min Act: -0.1700
Data Index: 8073604 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5668. Min Act: -0.1700
Data Index: 6988632 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5506. Min Act: -0.1700
Data Index: 1569945 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5506. Min Act: -0.1700
Data Index: 2303796 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6312. Min Range: -2.6312
Max Act: 2.5506. Min Act: -0.1700
Data Index: 2927035 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19