Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.8730. Min Act: -0.1700
Data Index: 6634343 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.7792. Min Act: -0.1700
Data Index: 1340216 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.7792. Min Act: -0.1700
Data Index: 6352762 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.6855. Min Act: -0.1700
Data Index: 8473919 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.6542. Min Act: -0.1700
Data Index: 8196089 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.6230. Min Act: -0.1700
Data Index: 330139 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.5917. Min Act: -0.1700
Data Index: 4326216 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.5917. Min Act: -0.1700
Data Index: 1864718 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.5292. Min Act: -0.1700
Data Index: 7495751 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.3417. Min Act: -0.1700
Data Index: 3603787 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.2792. Min Act: -0.1700
Data Index: 3539668 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.2480. Min Act: -0.1700
Data Index: 458518 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.2167. Min Act: -0.1700
Data Index: 7480975 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.2167. Min Act: -0.1700
Data Index: 468281 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.1855. Min Act: -0.1700
Data Index: 6395227 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.1855. Min Act: -0.1700
Data Index: 3846556 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.2167. Min Act: -0.1700
Data Index: 4187189 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.1230. Min Act: -0.1700
Data Index: 7230725 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.1542. Min Act: -0.1700
Data Index: 4342914 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8730. Min Range: -5.8730
Max Act: 5.1230. Min Act: -0.1700
Data Index: 6983207 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19