Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.7100. Min Act: -0.1700
Data Index: 1761162 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.6787. Min Act: -0.1700
Data Index: 5835797 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.4600. Min Act: -0.1700
Data Index: 1248595 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.4600. Min Act: -0.1700
Data Index: 4553778 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.4287. Min Act: -0.1700
Data Index: 1102903 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.4287. Min Act: -0.1700
Data Index: 2824734 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.3975. Min Act: -0.1700
Data Index: 96625 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.3037. Min Act: -0.1700
Data Index: 8234678 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.3037. Min Act: -0.1700
Data Index: 2316999 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.2725. Min Act: -0.1700
Data Index: 4104497 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.1162. Min Act: -0.1700
Data Index: 4710357 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.1162. Min Act: -0.1700
Data Index: 3510445 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.0850. Min Act: -0.1700
Data Index: 4262646 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.0850. Min Act: -0.1700
Data Index: 2777630 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.0850. Min Act: -0.1700
Data Index: 6864971 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.0537. Min Act: -0.1700
Data Index: 8408136 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.0537. Min Act: -0.1700
Data Index: 6409101 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7100. Min Range: -7.7100
Max Act: 6.9912. Min Act: -0.1700
Data Index: 4320602 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.0225. Min Act: -0.1700
Data Index: 7127540 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7100. Min Range: -7.7100
Max Act: 7.0225. Min Act: -0.1700
Data Index: 6558213 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19