Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.6892. Min Act: -0.1700
Data Index: 5888747 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.5955. Min Act: -0.1700
Data Index: 2118943 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.3142. Min Act: -0.1700
Data Index: 238858 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.1892. Min Act: -0.1700
Data Index: 5390144 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.1580. Min Act: -0.1700
Data Index: 2550421 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.0642. Min Act: -0.1700
Data Index: 538312 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.0642. Min Act: -0.1700
Data Index: 8704021 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.0330. Min Act: -0.1700
Data Index: 5784443 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6892. Min Range: -5.6892
Max Act: 5.0330. Min Act: -0.1700
Data Index: 2151602 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.9705. Min Act: -0.1700
Data Index: 3804572 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.9705. Min Act: -0.1700
Data Index: 436411 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.9080. Min Act: -0.1700
Data Index: 3308438 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.9080. Min Act: -0.1700
Data Index: 7310957 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.9080. Min Act: -0.1700
Data Index: 696296 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.9080. Min Act: -0.1700
Data Index: 8500301 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.9080. Min Act: -0.1700
Data Index: 4545203 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6552476 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.8767. Min Act: -0.1700
Data Index: 4817876 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.8767. Min Act: -0.1700
Data Index: 7697826 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6892. Min Range: -5.6892
Max Act: 4.8455. Min Act: -0.1700
Data Index: 6623764 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19