Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5857 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3389. Min Range: -6.3389
Max Act: 6.3389. Min Act: -0.1700
Data Index: 1133510 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3389. Min Range: -6.3389
Max Act: 6.2451. Min Act: -0.1700
Data Index: 3402898 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3389. Min Range: -6.3389
Max Act: 6.2139. Min Act: -0.1700
Data Index: 474240 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3389. Min Range: -6.3389
Max Act: 6.0889. Min Act: -0.1700
Data Index: 6630395 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3389. Min Range: -6.3389
Max Act: 6.0576. Min Act: -0.1700
Data Index: 3880944 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3389. Min Range: -6.3389
Max Act: 6.0264. Min Act: -0.1700
Data Index: 3127741 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9951. Min Act: -0.1700
Data Index: 5318939 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9951. Min Act: -0.1700
Data Index: 6169187 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9951. Min Act: -0.1700
Data Index: 4268356 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9639. Min Act: -0.1700
Data Index: 474234 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9639. Min Act: -0.1700
Data Index: 474230 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9326. Min Act: -0.1700
Data Index: 5208367 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9326. Min Act: -0.1700
Data Index: 3200158 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9326. Min Act: -0.1700
Data Index: 8624593 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9326. Min Act: -0.1700
Data Index: 8201813 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9326. Min Act: -0.1698
Data Index: 5278811 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9014. Min Act: -0.1700
Data Index: 4811861 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9014. Min Act: -0.1700
Data Index: 4811833 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9014. Min Act: -0.1699
Data Index: 2899440 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3389. Min Range: -6.3389
Max Act: 5.9014. Min Act: -0.1700
Data Index: 3817807 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19