Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5589 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3462. Min Range: -8.3462
Max Act: 8.3462. Min Act: -0.1700
Data Index: 4811806 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.4712. Min Act: -0.1700
Data Index: 6405077 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.3150. Min Act: -0.1700
Data Index: 1107028 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.2212. Min Act: -0.1700
Data Index: 3397251 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.1587. Min Act: -0.1700
Data Index: 6028865 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.1587. Min Act: -0.1700
Data Index: 7902119 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.1275. Min Act: -0.1700
Data Index: 8686364 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.0650. Min Act: -0.1700
Data Index: 4889174 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.0337. Min Act: -0.1700
Data Index: 3820223 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.0337. Min Act: -0.1700
Data Index: 2702205 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.0025. Min Act: -0.1700
Data Index: 7919106 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3462. Min Range: -8.3462
Max Act: 7.0025. Min Act: -0.1700
Data Index: 4060037 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.9712. Min Act: -0.1700
Data Index: 545654 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.9712. Min Act: -0.1700
Data Index: 409954 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.9087. Min Act: -0.1700
Data Index: 5890560 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.9087. Min Act: -0.1700
Data Index: 2928004 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.8775. Min Act: -0.1700
Data Index: 4692470 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.8775. Min Act: -0.1700
Data Index: 2731837 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.8775. Min Act: -0.1700
Data Index: 3214843 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3462. Min Range: -8.3462
Max Act: 6.8462. Min Act: -0.1700
Data Index: 872226 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19