Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.3733. Min Act: -0.1700
Data Index: 203222 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.2792. Min Act: -0.1700
Data Index: 7613795 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.2634. Min Act: -0.1700
Data Index: 1722286 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.2634. Min Act: -0.1700
Data Index: 2634856 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.2477. Min Act: -0.1700
Data Index: 928135 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.2320. Min Act: -0.1700
Data Index: 630340 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.2163. Min Act: -0.1700
Data Index: 7700646 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.2163. Min Act: -0.1700
Data Index: 6856855 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1849. Min Act: -0.1700
Data Index: 7009520 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1691. Min Act: -0.1700
Data Index: 7716547 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1849. Min Act: -0.1700
Data Index: 3700041 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1534. Min Act: -0.1700
Data Index: 2019503 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1534. Min Act: -0.1700
Data Index: 6639786 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1376. Min Act: -0.1700
Data Index: 2204627 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1219. Min Act: -0.1700
Data Index: 8398017 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.0904. Min Act: -0.1700
Data Index: 7788007 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.1061. Min Act: -0.1700
Data Index: 6609630 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.0904. Min Act: -0.1700
Data Index: 2344261 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.0904. Min Act: -0.1700
Data Index: 486920 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3733. Min Range: -3.3733
Max Act: 3.0746. Min Act: -0.1700
Data Index: 5282794 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19