Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4829 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.7547. Min Act: -0.1700
Data Index: 7536301 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.6297. Min Act: -0.1700
Data Index: 4001682 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.5984. Min Act: -0.1700
Data Index: 941690 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.5359. Min Act: -0.1700
Data Index: 7904014 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.5047. Min Act: -0.1700
Data Index: 4624647 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.4422. Min Act: -0.1700
Data Index: 4591853 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.4422. Min Act: -0.1700
Data Index: 6460980 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.4422. Min Act: -0.1700
Data Index: 2348959 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.4109. Min Act: -0.1700
Data Index: 2899171 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.3797. Min Act: -0.1700
Data Index: 2008205 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.3484. Min Act: -0.1700
Data Index: 4580837 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.3484. Min Act: -0.1700
Data Index: 6441131 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.3172. Min Act: -0.1700
Data Index: 8787454 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.2859. Min Act: -0.1700
Data Index: 794462 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.3172. Min Act: -0.1700
Data Index: 8170663 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.3172. Min Act: -0.1700
Data Index: 4077196 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.3172. Min Act: -0.1700
Data Index: 4713835 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.2859. Min Act: -0.1700
Data Index: 3350136 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.2859. Min Act: -0.1700
Data Index: 4862219 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7547. Min Range: -5.7547
Max Act: 5.2859. Min Act: -0.1700
Data Index: 6436837 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19