Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4597 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0616. Min Range: -6.0616
Max Act: 6.0616. Min Act: -0.1700
Data Index: 2258024 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.9054. Min Act: -0.1700
Data Index: 5291412 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.9054. Min Act: -0.1700
Data Index: 5660963 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.8741. Min Act: -0.1700
Data Index: 2761582 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.8429. Min Act: -0.1700
Data Index: 6868030 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.8429. Min Act: -0.1700
Data Index: 8168479 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.8116. Min Act: -0.1700
Data Index: 4007235 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7491. Min Act: -0.1700
Data Index: 7168737 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7804. Min Act: -0.1700
Data Index: 5707696 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7491. Min Act: -0.1700
Data Index: 2156164 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7491. Min Act: -0.1700
Data Index: 8499555 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7491. Min Act: -0.1700
Data Index: 4633157 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7179. Min Act: -0.1700
Data Index: 2226126 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7179. Min Act: -0.1700
Data Index: 7823653 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7179. Min Act: -0.1700
Data Index: 3480104 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.6866. Min Act: -0.1700
Data Index: 5694892 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.6866. Min Act: -0.1700
Data Index: 7641090 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.7179. Min Act: -0.1700
Data Index: 5895118 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.6554. Min Act: -0.1700
Data Index: 4154410 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0616. Min Range: -6.0616
Max Act: 5.6554. Min Act: -0.1700
Data Index: 558719 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19