Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.6279. Min Act: -0.1700
Data Index: 1312986 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.4404. Min Act: -0.1700
Data Index: 6448588 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.3779. Min Act: -0.1700
Data Index: 3932288 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.3466. Min Act: -0.1700
Data Index: 456171 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.3466. Min Act: -0.1700
Data Index: 3499803 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.3153. Min Act: -0.1700
Data Index: 3822628 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.2841. Min Act: -0.1700
Data Index: 4377950 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.2841. Min Act: -0.1700
Data Index: 5334985 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.2528. Min Act: -0.1700
Data Index: 2393139 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.2528. Min Act: -0.1700
Data Index: 962997 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.2216. Min Act: -0.1700
Data Index: 5337019 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1903. Min Act: -0.1700
Data Index: 452271 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.2216. Min Act: -0.1700
Data Index: 344312 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1903. Min Act: -0.1700
Data Index: 1206131 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1903. Min Act: -0.1700
Data Index: 8478101 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1591. Min Act: -0.1700
Data Index: 3270987 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1591. Min Act: -0.1700
Data Index: 624353 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1278. Min Act: -0.1700
Data Index: 3841199 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1591. Min Act: -0.1700
Data Index: 5890628 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6279. Min Range: -4.6279
Max Act: 4.1278. Min Act: -0.1700
Data Index: 4057504 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19