Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.9485. Min Act: -0.1700
Data Index: 182030 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.7610. Min Act: -0.1700
Data Index: 4695125 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.7297. Min Act: -0.1700
Data Index: 7544263 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.6985. Min Act: -0.1700
Data Index: 4063529 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.6672. Min Act: -0.1700
Data Index: 678660 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.5422. Min Act: -0.1700
Data Index: 1303128 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.5422. Min Act: -0.1700
Data Index: 7300919 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.4172. Min Act: -0.1700
Data Index: 5325105 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.4172. Min Act: -0.1700
Data Index: 4910127 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.3547. Min Act: -0.1700
Data Index: 674740 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.3860. Min Act: -0.1700
Data Index: 328119 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.3860. Min Act: -0.1700
Data Index: 4972181 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.3547. Min Act: -0.1700
Data Index: 1998886 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.3235. Min Act: -0.1700
Data Index: 2481411 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.3547. Min Act: -0.1700
Data Index: 7139857 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.3235. Min Act: -0.1700
Data Index: 6082336 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.2922. Min Act: -0.1700
Data Index: 2500475 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.2610. Min Act: -0.1700
Data Index: 4576636 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.2610. Min Act: -0.1700
Data Index: 4608445 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9485. Min Range: -6.9485
Max Act: 6.1985. Min Act: -0.1700
Data Index: 4910129 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19