Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1862 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 7240238 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.7259. Min Act: -0.1700
Data Index: 6683399 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6947. Min Act: -0.1700
Data Index: 1563325 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6947. Min Act: -0.1700
Data Index: 4694408 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6947. Min Act: -0.1700
Data Index: 1238732 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6634. Min Act: -0.1700
Data Index: 2445278 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6634. Min Act: -0.1700
Data Index: 433146 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6322. Min Act: -0.1700
Data Index: 8679001 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6009. Min Act: -0.1700
Data Index: 4098221 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6009. Min Act: -0.1700
Data Index: 563297 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.6322. Min Act: -0.1700
Data Index: 442713 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.5697. Min Act: -0.1700
Data Index: 6728332 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.5697. Min Act: -0.1700
Data Index: 7532210 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.5697. Min Act: -0.1700
Data Index: 63595 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.5384. Min Act: -0.1700
Data Index: 3293780 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.5384. Min Act: -0.1700
Data Index: 4162166 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.4759. Min Act: -0.1700
Data Index: 271627 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.5072. Min Act: -0.1700
Data Index: 3052355 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.4447. Min Act: -0.1700
Data Index: 5077496 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7572. Min Range: -5.7572
Max Act: 5.4134. Min Act: -0.1700
Data Index: 6199799 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19