Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4983. Min Range: -11.4983
Max Act: 11.4983. Min Act: -0.1700
Data Index: 2018260 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4983. Min Range: -11.4983
Max Act: 11.1233. Min Act: -0.1700
Data Index: 6595448 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4983. Min Range: -11.4983
Max Act: 11.0608. Min Act: -0.1700
Data Index: 3655805 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4983. Min Range: -11.4983
Max Act: 11.0608. Min Act: -0.1700
Data Index: 2751638 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4983. Min Range: -11.4983
Max Act: 11.0608. Min Act: -0.1700
Data Index: 3299951 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4983. Min Range: -11.4983
Max Act: 11.0608. Min Act: -0.1700
Data Index: 2193419 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.9983. Min Act: -0.1700
Data Index: 2730458 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.9983. Min Act: -0.1700
Data Index: 1257736 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.9983. Min Act: -0.1700
Data Index: 8794240 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.9358. Min Act: -0.1700
Data Index: 833186 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.9358. Min Act: -0.1700
Data Index: 4171300 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.9358. Min Act: -0.1700
Data Index: 8348215 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.8108. Min Act: -0.1700
Data Index: 5258269 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.8108. Min Act: -0.1700
Data Index: 8385066 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.8108. Min Act: -0.1700
Data Index: 5861861 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.8108. Min Act: -0.1700
Data Index: 3022052 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.8733. Min Act: -0.1700
Data Index: 8089804 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.8108. Min Act: -0.1700
Data Index: 7332965 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.7483. Min Act: -0.1700
Data Index: 5941350 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4983. Min Range: -11.4983
Max Act: 10.7483. Min Act: -0.1700
Data Index: 1408594 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19