Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1047. Min Range: -9.1047
Max Act: 9.0422. Min Act: -0.1700
Data Index: 3924955 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1047. Min Range: -9.1047
Max Act: 9.1047. Min Act: -0.1700
Data Index: 4957633 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.9797. Min Act: -0.1700
Data Index: 2055693 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.9172. Min Act: -0.1700
Data Index: 686555 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.8547. Min Act: -0.1700
Data Index: 7522498 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.9172. Min Act: -0.1700
Data Index: 4466956 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7922. Min Act: -0.1700
Data Index: 3580861 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7922. Min Act: -0.1700
Data Index: 4642373 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7922. Min Act: -0.1700
Data Index: 3694927 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7922. Min Act: -0.1700
Data Index: 398824 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7297. Min Act: -0.1700
Data Index: 4522139 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7297. Min Act: -0.1700
Data Index: 3484089 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7297. Min Act: -0.1700
Data Index: 1957238 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7297. Min Act: -0.1700
Data Index: 2870393 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7297. Min Act: -0.1700
Data Index: 4723789 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.6672. Min Act: -0.1700
Data Index: 509869 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.7297. Min Act: -0.1700
Data Index: 4707253 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.6672. Min Act: -0.1700
Data Index: 6079048 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.6672. Min Act: -0.1700
Data Index: 1359907 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1047. Min Range: -9.1047
Max Act: 8.6047. Min Act: -0.1700
Data Index: 7466617 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19