Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1011. Min Range: -5.1011
Max Act: 5.1011. Min Act: -0.1700
Data Index: 1817548 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1011. Min Range: -5.1011
Max Act: 5.0699. Min Act: -0.1700
Data Index: 3322056 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1011. Min Range: -5.1011
Max Act: 5.0386. Min Act: -0.1700
Data Index: 3397919 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1011. Min Range: -5.1011
Max Act: 5.0386. Min Act: -0.1700
Data Index: 8426851 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1011. Min Range: -5.1011
Max Act: 5.0074. Min Act: -0.1700
Data Index: 2954341 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1011. Min Range: -5.1011
Max Act: 5.0074. Min Act: -0.1700
Data Index: 4053926 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1011. Min Range: -5.1011
Max Act: 5.0074. Min Act: -0.1700
Data Index: 2361065 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9449. Min Act: -0.1700
Data Index: 4679100 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9761. Min Act: -0.1700
Data Index: 4017733 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9449. Min Act: -0.1700
Data Index: 1240407 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9449. Min Act: -0.1700
Data Index: 219378 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9449. Min Act: -0.1700
Data Index: 3163350 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9449. Min Act: -0.1700
Data Index: 8192256 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9136. Min Act: -0.1700
Data Index: 7527860 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.9136. Min Act: -0.1700
Data Index: 7186335 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.8824. Min Act: -0.1700
Data Index: 8703160 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.8824. Min Act: -0.1700
Data Index: 8660471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.8824. Min Act: -0.1700
Data Index: 6984472 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.8511. Min Act: -0.1700
Data Index: 2376139 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1011. Min Range: -5.1011
Max Act: 4.8511. Min Act: -0.1700
Data Index: 4063875 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19