Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2174 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.7628. Min Act: -0.1700
Data Index: 5001244 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.6065. Min Act: -0.1700
Data Index: 8194335 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.5440. Min Act: -0.1700
Data Index: 927801 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.5440. Min Act: -0.1700
Data Index: 3485164 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.4815. Min Act: -0.1700
Data Index: 5654847 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.4503. Min Act: -0.1700
Data Index: 251017 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.4503. Min Act: -0.1700
Data Index: 6268248 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.4503. Min Act: -0.1700
Data Index: 5568435 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.4190. Min Act: -0.1700
Data Index: 8282785 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.3565. Min Act: -0.1700
Data Index: 8598175 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.3253. Min Act: -0.1700
Data Index: 2121274 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2940. Min Act: -0.1700
Data Index: 32393 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2940. Min Act: -0.1700
Data Index: 6398495 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2940. Min Act: -0.1700
Data Index: 5963728 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2940. Min Act: -0.1700
Data Index: 8058573 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2940. Min Act: -0.1700
Data Index: 2085761 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2628. Min Act: -0.1700
Data Index: 4540154 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2628. Min Act: -0.1700
Data Index: 3420489 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2628. Min Act: -0.1700
Data Index: 5625495 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2628. Min Act: -0.1700
Data Index: 8487755 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19