Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5117 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0462. Min Range: -6.0462
Max Act: 6.0462. Min Act: -0.1700
Data Index: 1455369 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.9837. Min Act: -0.1700
Data Index: 8756444 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.9837. Min Act: -0.1700
Data Index: 242385 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2380831 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.8900. Min Act: -0.1700
Data Index: 6580832 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.6712. Min Act: -0.1700
Data Index: 3448018 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.7025. Min Act: -0.1700
Data Index: 6580827 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.6400. Min Act: -0.1700
Data Index: 1256838 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.6087. Min Act: -0.1700
Data Index: 3018521 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.6087. Min Act: -0.1700
Data Index: 6001144 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.6087. Min Act: -0.1700
Data Index: 6001145 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 4056378 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 5693381 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.5150. Min Act: -0.1700
Data Index: 5045470 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.4837. Min Act: -0.1700
Data Index: 6580816 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.4837. Min Act: -0.1700
Data Index: 5484164 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.4837. Min Act: -0.1700
Data Index: 3770656 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.4837. Min Act: -0.1700
Data Index: 3448019 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.4525. Min Act: -0.1700
Data Index: 856247 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0462. Min Range: -6.0462
Max Act: 5.4525. Min Act: -0.1700
Data Index: 1256851 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19