Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5951 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1730. Min Range: -5.1730
Max Act: 5.1730. Min Act: -0.1700
Data Index: 6464553 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1730. Min Range: -5.1730
Max Act: 5.1105. Min Act: -0.1700
Data Index: 8670150 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1730. Min Range: -5.1730
Max Act: 5.0167. Min Act: -0.1700
Data Index: 3563069 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9855. Min Act: -0.1700
Data Index: 2315386 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 5414340 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9542. Min Act: -0.1700
Data Index: 3558521 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 1400449 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9542. Min Act: -0.1700
Data Index: 1532297 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9542. Min Act: -0.1700
Data Index: 5001948 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9542. Min Act: -0.1700
Data Index: 4123469 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 3185075 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 106681 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 3563064 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 3563066 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 1877552 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.9230. Min Act: -0.1700
Data Index: 7400265 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4150806 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.8917. Min Act: -0.1700
Data Index: 1621429 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4198652 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1730. Min Range: -5.1730
Max Act: 4.8917. Min Act: -0.1700
Data Index: 5046253 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19