Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2078. Min Range: -6.2078
Max Act: 6.2078. Min Act: -0.1700
Data Index: 8575180 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2078. Min Range: -6.2078
Max Act: 6.1140. Min Act: -0.1700
Data Index: 1628699 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2078. Min Range: -6.2078
Max Act: 6.0828. Min Act: -0.1700
Data Index: 5332332 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2078. Min Range: -6.2078
Max Act: 6.0828. Min Act: -0.1700
Data Index: 1087811 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2078. Min Range: -6.2078
Max Act: 6.0515. Min Act: -0.1700
Data Index: 280549 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9890. Min Act: -0.1700
Data Index: 8728577 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9890. Min Act: -0.1700
Data Index: 5271024 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9578. Min Act: -0.1700
Data Index: 1298365 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9578. Min Act: -0.1700
Data Index: 2463963 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9265. Min Act: -0.1700
Data Index: 6804971 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9578. Min Act: -0.1700
Data Index: 4983080 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9265. Min Act: -0.1700
Data Index: 5355723 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8953. Min Act: -0.1700
Data Index: 2299607 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8328. Min Act: -0.1700
Data Index: 5452354 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8015. Min Act: -0.1700
Data Index: 2463966 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8015. Min Act: -0.1700
Data Index: 748443 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8015. Min Act: -0.1700
Data Index: 101644 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8015. Min Act: -0.1700
Data Index: 6547481 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.7703. Min Act: -0.1700
Data Index: 5474731 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.7703. Min Act: -0.1700
Data Index: 7474773 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19