Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1077. Min Range: -7.1077
Max Act: 7.1077. Min Act: -0.1700
Data Index: 3103294 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1077. Min Range: -7.1077
Max Act: 7.0452. Min Act: -0.1700
Data Index: 1247784 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.9202. Min Act: -0.1700
Data Index: 486998 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.9202. Min Act: -0.1700
Data Index: 7261066 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.9202. Min Act: -0.1700
Data Index: 4622452 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.8577. Min Act: -0.1700
Data Index: 7163493 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.8577. Min Act: -0.1700
Data Index: 3501199 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.8577. Min Act: -0.1700
Data Index: 6550080 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.8577. Min Act: -0.1700
Data Index: 1029438 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.8264. Min Act: -0.1700
Data Index: 8146418 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.8264. Min Act: -0.1700
Data Index: 1332911 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.8264. Min Act: -0.1700
Data Index: 6112838 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7952. Min Act: -0.1700
Data Index: 7863758 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7639. Min Act: -0.1700
Data Index: 3009162 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7639. Min Act: -0.1700
Data Index: 1754971 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7327. Min Act: -0.1700
Data Index: 695099 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7327. Min Act: -0.1700
Data Index: 727349 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7327. Min Act: -0.1700
Data Index: 147791 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7014. Min Act: -0.1700
Data Index: 1311544 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1077. Min Range: -7.1077
Max Act: 6.7014. Min Act: -0.1700
Data Index: 983982 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19