Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5576 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.3070. Min Act: -0.1700
Data Index: 4320648 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.2757. Min Act: -0.1700
Data Index: 1089571 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.2445. Min Act: -0.1700
Data Index: 2730161 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.2757. Min Act: -0.1700
Data Index: 4012263 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1820. Min Act: -0.1700
Data Index: 5205672 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1507. Min Act: -0.1700
Data Index: 6959613 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1507. Min Act: -0.1700
Data Index: 7712549 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 3811370 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 6435892 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 6219887 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 3482977 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 5328151 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 4960206 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.0882. Min Act: -0.1700
Data Index: 3470227 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 8398294 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.0882. Min Act: -0.1700
Data Index: 1247063 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.0882. Min Act: -0.1700
Data Index: 4463300 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.1195. Min Act: -0.1700
Data Index: 6204224 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.0570. Min Act: -0.1700
Data Index: 3811371 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3070. Min Range: -6.3070
Max Act: 6.0570. Min Act: -0.1700
Data Index: 905548 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19