Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.8169. Min Act: -0.1700
Data Index: 5594554 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.7544. Min Act: -0.1700
Data Index: 6832669 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.6919. Min Act: -0.1700
Data Index: 8292361 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.6294. Min Act: -0.1700
Data Index: 1425970 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.6294. Min Act: -0.1700
Data Index: 3342966 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.5669. Min Act: -0.1700
Data Index: 1693886 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.5669. Min Act: -0.1700
Data Index: 4737243 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.4732. Min Act: -0.1700
Data Index: 748913 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.4419. Min Act: -0.1700
Data Index: 4102328 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.4419. Min Act: -0.1700
Data Index: 4542910 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.4419. Min Act: -0.1700
Data Index: 8202629 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.4107. Min Act: -0.1700
Data Index: 240132 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.4107. Min Act: -0.1700
Data Index: 601470 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.4107. Min Act: -0.1700
Data Index: 6023869 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.3794. Min Act: -0.1700
Data Index: 4198619 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.3482. Min Act: -0.1700
Data Index: 4268408 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.3482. Min Act: -0.1700
Data Index: 6432217 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.3169. Min Act: -0.1700
Data Index: 4772942 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.3169. Min Act: -0.1700
Data Index: 3616649 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8169. Min Range: -6.8169
Max Act: 6.3169. Min Act: -0.1700
Data Index: 6398737 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19