Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 434 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0592. Min Range: -8.0592
Max Act: 8.0592. Min Act: -0.1700
Data Index: 2588507 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.9967. Min Act: -0.1700
Data Index: 8320752 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.8717. Min Act: -0.1700
Data Index: 313357 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.7467. Min Act: -0.1700
Data Index: 8748344 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.6842. Min Act: -0.1700
Data Index: 4668941 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.6529. Min Act: -0.1700
Data Index: 3248648 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.5904. Min Act: -0.1700
Data Index: 2281336 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.5592. Min Act: -0.1700
Data Index: 5869361 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.5904. Min Act: -0.1700
Data Index: 3299434 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.5279. Min Act: -0.1700
Data Index: 7477638 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.5592. Min Act: -0.1700
Data Index: 4861244 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.5592. Min Act: -0.1700
Data Index: 2300251 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.5279. Min Act: -0.1700
Data Index: 3299433 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.4654. Min Act: -0.1700
Data Index: 5856851 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.4967. Min Act: -0.1700
Data Index: 7477636 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.4654. Min Act: -0.1700
Data Index: 4163001 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.4654. Min Act: -0.1700
Data Index: 8269841 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.4654. Min Act: -0.1700
Data Index: 5981290 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.4029. Min Act: -0.1700
Data Index: 6387287 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0592. Min Range: -8.0592
Max Act: 7.4029. Min Act: -0.1700
Data Index: 5621436 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19