Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0198. Min Range: -9.0198
Max Act: 9.0198. Min Act: -0.1700
Data Index: 6009523 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0198. Min Range: -9.0198
Max Act: 9.0198. Min Act: -0.1700
Data Index: 435392 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.8323. Min Act: -0.1700
Data Index: 8721213 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.6448. Min Act: -0.1700
Data Index: 4193446 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.6448. Min Act: -0.1700
Data Index: 7220136 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.7073. Min Act: -0.1700
Data Index: 6848501 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.7073. Min Act: -0.1700
Data Index: 6441731 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.6448. Min Act: -0.1700
Data Index: 3257118 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.6448. Min Act: -0.1700
Data Index: 8803117 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5823. Min Act: -0.1700
Data Index: 1267729 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5823. Min Act: -0.1700
Data Index: 808622 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5823. Min Act: -0.1700
Data Index: 8207675 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5823. Min Act: -0.1700
Data Index: 7310439 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5198. Min Act: -0.1700
Data Index: 8333970 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5198. Min Act: -0.1700
Data Index: 7064988 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5198. Min Act: -0.1700
Data Index: 6381582 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.4573. Min Act: -0.1700
Data Index: 8528172 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.5198. Min Act: -0.1700
Data Index: 4472793 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.4573. Min Act: -0.1700
Data Index: 8032630 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0198. Min Range: -9.0198
Max Act: 8.4573. Min Act: -0.1700
Data Index: 2206698 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19