Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2186 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.4730. Min Act: -0.1700
Data Index: 3512486 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.3480. Min Act: -0.1700
Data Index: 4856188 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.2855. Min Act: -0.1700
Data Index: 541674 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.2230. Min Act: -0.1700
Data Index: 872829 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.2230. Min Act: -0.1700
Data Index: 596801 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.0980. Min Act: -0.1700
Data Index: 3370121 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.0355. Min Act: -0.1700
Data Index: 779259 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.4730. Min Range: -14.4730
Max Act: 14.0355. Min Act: -0.1700
Data Index: 305949 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.8480. Min Act: -0.1700
Data Index: 8010427 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.9105. Min Act: -0.1700
Data Index: 5702938 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7855. Min Act: -0.1700
Data Index: 3003397 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7855. Min Act: -0.1700
Data Index: 1888030 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7855. Min Act: -0.1700
Data Index: 5740465 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.8480. Min Act: -0.1700
Data Index: 4644927 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7855. Min Act: -0.1700
Data Index: 6774130 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7855. Min Act: -0.1700
Data Index: 4098864 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7230. Min Act: -0.1700
Data Index: 1957160 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.6605. Min Act: -0.1700
Data Index: 5767413 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7230. Min Act: -0.1700
Data Index: 3896409 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.4730. Min Range: -14.4730
Max Act: 13.7230. Min Act: -0.1700
Data Index: 2093651 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19