Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5060 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.6477. Min Act: -0.1700
Data Index: 6052000 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.5540. Min Act: -0.1700
Data Index: 6817279 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.5227. Min Act: -0.1700
Data Index: 8518781 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.5227. Min Act: -0.1700
Data Index: 2521489 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3977. Min Act: -0.1700
Data Index: 8305504 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3977. Min Act: -0.1700
Data Index: 6514919 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3977. Min Act: -0.1700
Data Index: 5138320 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3665. Min Act: -0.1700
Data Index: 2496157 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3665. Min Act: -0.1700
Data Index: 2589078 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3352. Min Act: -0.1700
Data Index: 7480734 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3352. Min Act: -0.1700
Data Index: 1889506 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3352. Min Act: -0.1700
Data Index: 1804838 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.3040. Min Act: -0.1700
Data Index: 8030344 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.2727. Min Act: -0.1700
Data Index: 1056520 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.2727. Min Act: -0.1700
Data Index: 3721927 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.2727. Min Act: -0.1700
Data Index: 7210621 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.2727. Min Act: -0.1700
Data Index: 4361413 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.2415. Min Act: -0.1700
Data Index: 2039713 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.2727. Min Act: -0.1700
Data Index: 2195412 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6477. Min Range: -6.6477
Max Act: 6.2415. Min Act: -0.1700
Data Index: 7062361 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19