Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.9496. Min Act: -0.1700
Data Index: 4952546 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.6683. Min Act: -0.1700
Data Index: 7679644 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.6058. Min Act: -0.1700
Data Index: 73546 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.5433. Min Act: -0.1700
Data Index: 2203110 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.4808. Min Act: -0.1700
Data Index: 5676844 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.4808. Min Act: -0.1700
Data Index: 6431107 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.4808. Min Act: -0.1700
Data Index: 4141837 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.4183. Min Act: -0.1700
Data Index: 4759928 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3871. Min Act: -0.1700
Data Index: 4428313 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3871. Min Act: -0.1700
Data Index: 3368610 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3871. Min Act: -0.1700
Data Index: 8499056 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3871. Min Act: -0.1700
Data Index: 3516496 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3558. Min Act: -0.1700
Data Index: 7147068 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3558. Min Act: -0.1700
Data Index: 391047 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3558. Min Act: -0.1700
Data Index: 4334522 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3558. Min Act: -0.1700
Data Index: 5678670 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3558. Min Act: -0.1700
Data Index: 4204477 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3246. Min Act: -0.1700
Data Index: 340249 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3246. Min Act: -0.1700
Data Index: 5761839 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9496. Min Range: -5.9496
Max Act: 5.3246. Min Act: -0.1700
Data Index: 6795888 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19