Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1359 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3576. Min Range: -7.3576
Max Act: 7.3576. Min Act: -0.1700
Data Index: 3284343 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3576. Min Range: -7.3576
Max Act: 7.2951. Min Act: -0.1700
Data Index: 7371055 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3576. Min Range: -7.3576
Max Act: 7.1701. Min Act: -0.1700
Data Index: 7594717 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3576. Min Range: -7.3576
Max Act: 7.1701. Min Act: -0.1700
Data Index: 5409040 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3576. Min Range: -7.3576
Max Act: 7.1389. Min Act: -0.1700
Data Index: 5374035 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3576. Min Range: -7.3576
Max Act: 7.0764. Min Act: -0.1700
Data Index: 2507310 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3576. Min Range: -7.3576
Max Act: 7.0139. Min Act: -0.1700
Data Index: 2393172 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.9826. Min Act: -0.1700
Data Index: 2026364 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.9826. Min Act: -0.1700
Data Index: 305009 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.9201. Min Act: -0.1700
Data Index: 7970357 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.8889. Min Act: -0.1700
Data Index: 1791702 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.8576. Min Act: -0.1700
Data Index: 7711899 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.8576. Min Act: -0.1700
Data Index: 4190216 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.8264. Min Act: -0.1700
Data Index: 3551295 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.7951. Min Act: -0.1700
Data Index: 3619091 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.7951. Min Act: -0.1700
Data Index: 2324521 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.7639. Min Act: -0.1700
Data Index: 7001208 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.7951. Min Act: -0.1700
Data Index: 7371056 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.7951. Min Act: -0.1700
Data Index: 1967578 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3576. Min Range: -7.3576
Max Act: 6.7951. Min Act: -0.1700
Data Index: 8143003 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19