Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 79 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.3268. Min Act: -0.1700
Data Index: 6224015 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 6001077 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 5048183 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 8754941 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.1393. Min Act: -0.1700
Data Index: 601417 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.1080. Min Act: -0.1700
Data Index: 8701612 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.0455. Min Act: -0.1700
Data Index: 8322784 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.0143. Min Act: -0.1700
Data Index: 6863050 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.0455. Min Act: -0.1700
Data Index: 728960 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.0143. Min Act: -0.1700
Data Index: 728957 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3268. Min Range: -7.3268
Max Act: 7.0455. Min Act: -0.1700
Data Index: 2498089 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9830. Min Act: -0.1700
Data Index: 535018 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9830. Min Act: -0.1700
Data Index: 8124447 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9830. Min Act: -0.1700
Data Index: 7498904 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9518. Min Act: -0.1700
Data Index: 1602598 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9518. Min Act: -0.1700
Data Index: 2271922 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9205. Min Act: -0.1700
Data Index: 7467394 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9518. Min Act: -0.1700
Data Index: 7222623 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9518. Min Act: -0.1700
Data Index: 5895273 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3268. Min Range: -7.3268
Max Act: 6.9518. Min Act: -0.1700
Data Index: 5546830 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19