Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5451 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.6249. Min Act: -0.1700
Data Index: 1017721 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.5624. Min Act: -0.1700
Data Index: 257587 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.5311. Min Act: -0.1700
Data Index: 968307 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.4999. Min Act: -0.1700
Data Index: 6980801 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.4686. Min Act: -0.1700
Data Index: 4452160 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.4374. Min Act: -0.1700
Data Index: 1575467 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.4061. Min Act: -0.1700
Data Index: 1893519 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.4061. Min Act: -0.1700
Data Index: 8194202 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.4061. Min Act: -0.1700
Data Index: 541534 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3749. Min Act: -0.1700
Data Index: 800036 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3749. Min Act: -0.1700
Data Index: 8235263 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 1448589 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.4061. Min Act: -0.1700
Data Index: 5907015 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 7732354 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 747522 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 1270571 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 711068 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 4614347 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 5196313 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6249. Min Range: -5.6249
Max Act: 5.3436. Min Act: -0.1700
Data Index: 5630050 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19