Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1197 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3293. Min Range: -5.3293
Max Act: 5.3293. Min Act: -0.1700
Data Index: 539885 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3293. Min Range: -5.3293
Max Act: 5.1730. Min Act: -0.1700
Data Index: 5092411 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3293. Min Range: -5.3293
Max Act: 5.0168. Min Act: -0.1700
Data Index: 1870525 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3293. Min Range: -5.3293
Max Act: 5.0480. Min Act: -0.1700
Data Index: 3375758 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3293. Min Range: -5.3293
Max Act: 5.0168. Min Act: -0.1700
Data Index: 1686563 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3293. Min Range: -5.3293
Max Act: 5.0168. Min Act: -0.1700
Data Index: 678016 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9855. Min Act: -0.1700
Data Index: 5767059 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9855. Min Act: -0.1700
Data Index: 5061537 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9855. Min Act: -0.1700
Data Index: 6859999 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9855. Min Act: -0.1700
Data Index: 3815954 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9543. Min Act: -0.1700
Data Index: 6782118 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9230. Min Act: -0.1700
Data Index: 7972656 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.8918. Min Act: -0.1700
Data Index: 1513731 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9230. Min Act: -0.1700
Data Index: 2009092 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.9543. Min Act: -0.1700
Data Index: 7060335 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.8918. Min Act: -0.1700
Data Index: 4898887 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.8918. Min Act: -0.1700
Data Index: 8186336 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.8605. Min Act: -0.1700
Data Index: 6725981 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.8605. Min Act: -0.1700
Data Index: 8307827 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3293. Min Range: -5.3293
Max Act: 4.8605. Min Act: -0.1700
Data Index: 7232298 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19