Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2368 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.4510. Min Act: -0.1700
Data Index: 451813 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.4510. Min Act: -0.1700
Data Index: 1384401 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.4353. Min Act: -0.1700
Data Index: 4681318 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.4197. Min Act: -0.1700
Data Index: 5234091 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.3883. Min Act: -0.1700
Data Index: 6315345 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.3883. Min Act: -0.1700
Data Index: 8778280 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.2942. Min Act: -0.1700
Data Index: 4717746 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.2471. Min Act: -0.1700
Data Index: 547850 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.2313. Min Act: -0.1700
Data Index: 5682096 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.2156. Min Act: -0.1700
Data Index: 1145742 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1999. Min Act: -0.1700
Data Index: 3427028 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1999. Min Act: -0.1700
Data Index: 8312306 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1999. Min Act: -0.1700
Data Index: 3237117 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1842. Min Act: -0.1700
Data Index: 6363135 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1842. Min Act: -0.1700
Data Index: 2351649 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1684. Min Act: -0.1700
Data Index: 5545581 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1684. Min Act: -0.1700
Data Index: 912733 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1527. Min Act: -0.1700
Data Index: 5970587 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1684. Min Act: -0.1700
Data Index: 2780834 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4510. Min Range: -3.4510
Max Act: 3.1527. Min Act: -0.1700
Data Index: 633701 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19