Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2543 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.6650. Min Act: -0.1700
Data Index: 8261913 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.4775. Min Act: -0.1700
Data Index: 103396 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.3838. Min Act: -0.1700
Data Index: 5615780 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.3525. Min Act: -0.1700
Data Index: 2319560 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.3525. Min Act: -0.1700
Data Index: 4475401 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.3213. Min Act: -0.1700
Data Index: 6819589 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.2900. Min Act: -0.1700
Data Index: 5319082 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.2275. Min Act: -0.1700
Data Index: 3791927 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1963. Min Act: -0.1700
Data Index: 600059 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1963. Min Act: -0.1700
Data Index: 5669026 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.2275. Min Act: -0.1700
Data Index: 7309459 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.2275. Min Act: -0.1700
Data Index: 4209781 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.2275. Min Act: -0.1700
Data Index: 6114248 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1963. Min Act: -0.1700
Data Index: 3467566 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1650. Min Act: -0.1700
Data Index: 1093301 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1650. Min Act: -0.1700
Data Index: 7438904 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1963. Min Act: -0.1700
Data Index: 5832685 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1338. Min Act: -0.1700
Data Index: 4907583 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1338. Min Act: -0.1700
Data Index: 1372286 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6650. Min Range: -6.6650
Max Act: 6.1338. Min Act: -0.1700
Data Index: 3464350 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19