Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1897 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4272. Min Range: -3.4272
Max Act: 3.4272. Min Act: -0.1700
Data Index: 1346319 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4272. Min Range: -3.4272
Max Act: 3.1602. Min Act: -0.1700
Data Index: 7317515 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4272. Min Range: -3.4272
Max Act: 3.0657. Min Act: -0.1700
Data Index: 1556478 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4272. Min Range: -3.4272
Max Act: 3.0499. Min Act: -0.1700
Data Index: 3152647 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4272. Min Range: -3.4272
Max Act: 3.0499. Min Act: -0.1700
Data Index: 2923331 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4272. Min Range: -3.4272
Max Act: 3.0341. Min Act: -0.1700
Data Index: 3187410 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4272. Min Range: -3.4272
Max Act: 3.0183. Min Act: -0.1700
Data Index: 8812147 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.9867. Min Act: -0.1700
Data Index: 4689688 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.9551. Min Act: -0.1700
Data Index: 3483112 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.9551. Min Act: -0.1700
Data Index: 24634 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.9551. Min Act: -0.1700
Data Index: 5965876 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8917. Min Act: -0.1700
Data Index: 1560389 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.9076. Min Act: -0.1700
Data Index: 5522897 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8917. Min Act: -0.1700
Data Index: 6902255 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8758. Min Act: -0.1700
Data Index: 2222646 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8600. Min Act: -0.1700
Data Index: 4771307 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8441. Min Act: -0.1700
Data Index: 2677671 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8282. Min Act: -0.1700
Data Index: 6223148 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8441. Min Act: -0.1700
Data Index: 4130559 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4272. Min Range: -3.4272
Max Act: 2.8441. Min Act: -0.1700
Data Index: 2373883 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19