Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4462 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2418. Min Range: -7.2418
Max Act: 7.2418. Min Act: -0.1700
Data Index: 91084 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.8356. Min Act: -0.1700
Data Index: 114969 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.6793. Min Act: -0.1700
Data Index: 3807914 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.6168. Min Act: -0.1700
Data Index: 198725 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.5543. Min Act: -0.1700
Data Index: 5653675 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.4293. Min Act: -0.1700
Data Index: 4010777 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.4293. Min Act: -0.1700
Data Index: 4520475 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.4293. Min Act: -0.1700
Data Index: 5459779 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3981. Min Act: -0.1700
Data Index: 8117865 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3356. Min Act: -0.1700
Data Index: 1927057 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3356. Min Act: -0.1700
Data Index: 2434667 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3356. Min Act: -0.1700
Data Index: 3641314 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3356. Min Act: -0.1699
Data Index: 7858760 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3356. Min Act: -0.1700
Data Index: 1844328 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3043. Min Act: -0.1700
Data Index: 128056 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.3043. Min Act: -0.1700
Data Index: 780352 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.2731. Min Act: -0.1700
Data Index: 5853266 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.2731. Min Act: -0.1700
Data Index: 1034353 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.2731. Min Act: -0.1700
Data Index: 5043037 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2418. Min Range: -7.2418
Max Act: 6.2106. Min Act: -0.1700
Data Index: 1113110 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19