Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.6273. Min Act: -0.1700
Data Index: 5332638 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.5336. Min Act: -0.1700
Data Index: 5116786 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.4398. Min Act: -0.1700
Data Index: 4257742 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.4398. Min Act: -0.1700
Data Index: 6640701 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.3148. Min Act: -0.1700
Data Index: 5241060 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.2211. Min Act: -0.1700
Data Index: 2191173 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.1585. Min Act: -0.1700
Data Index: 3665078 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.1898. Min Act: -0.1700
Data Index: 8245611 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.1585. Min Act: -0.1700
Data Index: 7238378 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.1585. Min Act: -0.1700
Data Index: 7656668 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.1273. Min Act: -0.1700
Data Index: 853962 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0960. Min Act: -0.1700
Data Index: 2278871 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0960. Min Act: -0.1700
Data Index: 8064261 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0648. Min Act: -0.1700
Data Index: 3006485 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0335. Min Act: -0.1700
Data Index: 1933074 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0648. Min Act: -0.1700
Data Index: 2928450 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0648. Min Act: -0.1700
Data Index: 4933704 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0648. Min Act: -0.1700
Data Index: 216485 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0648. Min Act: -0.1700
Data Index: 8590375 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6273. Min Range: -4.6273
Max Act: 4.0335. Min Act: -0.1700
Data Index: 563169 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19