Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.8525. Min Act: -0.1700
Data Index: 319735 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.7275. Min Act: -0.1700
Data Index: 1960932 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.7275. Min Act: -0.1700
Data Index: 3272562 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.6650. Min Act: -0.1700
Data Index: 2214003 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.4775. Min Act: -0.1700
Data Index: 3912869 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.4775. Min Act: -0.1700
Data Index: 8662749 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.3525. Min Act: -0.1700
Data Index: 4916193 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.3525. Min Act: -0.1700
Data Index: 3777281 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.3525. Min Act: -0.1700
Data Index: 5156828 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2900. Min Act: -0.1700
Data Index: 6264253 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2900. Min Act: -0.1700
Data Index: 5867765 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2275. Min Act: -0.1700
Data Index: 3679494 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2275. Min Act: -0.1700
Data Index: 3316749 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2275. Min Act: -0.1700
Data Index: 4940258 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2275. Min Act: -0.1700
Data Index: 7545850 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2275. Min Act: -0.1700
Data Index: 2315054 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2275. Min Act: -0.1700
Data Index: 4595080 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.1650. Min Act: -0.1700
Data Index: 6811199 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.2275. Min Act: -0.1700
Data Index: 6708584 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8525. Min Range: -9.8525
Max Act: 9.1650. Min Act: -0.1700
Data Index: 2128738 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19