Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0662. Min Range: -7.0662
Max Act: 7.0662. Min Act: -0.1700
Data Index: 4796254 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0662. Min Range: -7.0662
Max Act: 7.0037. Min Act: -0.1700
Data Index: 4756425 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.9412. Min Act: -0.1700
Data Index: 2695430 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.8787. Min Act: -0.1700
Data Index: 334406 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.7537. Min Act: -0.1700
Data Index: 1937965 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.7224. Min Act: -0.1700
Data Index: 7072191 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.7537. Min Act: -0.1700
Data Index: 4313790 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6912. Min Act: -0.1700
Data Index: 1979714 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.7224. Min Act: -0.1700
Data Index: 3015805 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6912. Min Act: -0.1700
Data Index: 730309 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6912. Min Act: -0.1700
Data Index: 5390216 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6599. Min Act: -0.1700
Data Index: 8818425 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.5974. Min Act: -0.1700
Data Index: 2881326 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6287. Min Act: -0.1700
Data Index: 6296314 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6287. Min Act: -0.1700
Data Index: 2548833 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6287. Min Act: -0.1700
Data Index: 3311143 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6287. Min Act: -0.1700
Data Index: 5155447 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6287. Min Act: -0.1700
Data Index: 3792405 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.6287. Min Act: -0.1700
Data Index: 6335524 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0662. Min Range: -7.0662
Max Act: 6.5974. Min Act: -0.1700
Data Index: 4450488 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19