Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.3481. Min Act: -0.1700
Data Index: 6661749 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9731. Min Act: -0.1700
Data Index: 7219842 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.6919. Min Act: -0.1700
Data Index: 1517327 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.6919. Min Act: -0.1700
Data Index: 6289770 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.6919. Min Act: -0.1700
Data Index: 5530016 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.6919. Min Act: -0.1700
Data Index: 4647524 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.6919. Min Act: -0.1700
Data Index: 7807409 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.6606. Min Act: -0.1700
Data Index: 6617243 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.6294. Min Act: -0.1700
Data Index: 7667530 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5981. Min Act: -0.1700
Data Index: 2155023 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5981. Min Act: -0.1700
Data Index: 6617783 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5981. Min Act: -0.1700
Data Index: 6002665 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5981. Min Act: -0.1700
Data Index: 4589024 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5981. Min Act: -0.1700
Data Index: 8386349 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5669. Min Act: -0.1700
Data Index: 5105667 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5356. Min Act: -0.1700
Data Index: 7807410 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5356. Min Act: -0.1700
Data Index: 4080038 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5044. Min Act: -0.1700
Data Index: 181514 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.5044. Min Act: -0.1700
Data Index: 6198302 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.4731. Min Act: -0.1700
Data Index: 2994383 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19