Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1623. Min Range: -4.1623
Max Act: 4.1623. Min Act: -0.1700
Data Index: 4549256 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1623. Min Range: -4.1623
Max Act: 4.1310. Min Act: -0.1700
Data Index: 4549254 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1623. Min Range: -4.1623
Max Act: 4.1310. Min Act: -0.1700
Data Index: 4549255 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1623. Min Range: -4.1623
Max Act: 4.1310. Min Act: -0.1700
Data Index: 4075206 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1623. Min Range: -4.1623
Max Act: 4.1310. Min Act: -0.1700
Data Index: 4549257 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.9748. Min Act: -0.1700
Data Index: 4523027 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.9748. Min Act: -0.1700
Data Index: 4075205 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.9122. Min Act: -0.1700
Data Index: 7904247 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.9122. Min Act: -0.1700
Data Index: 4437958 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.8810. Min Act: -0.1700
Data Index: 317169 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.8184. Min Act: -0.1700
Data Index: 1832889 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.8184. Min Act: -0.1700
Data Index: 4985018 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.7559. Min Act: -0.1700
Data Index: 5212767 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6620. Min Act: -0.1700
Data Index: 1832884 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6933. Min Act: -0.1700
Data Index: 5527042 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6307. Min Act: -0.1700
Data Index: 3935402 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6307. Min Act: -0.1700
Data Index: 6386829 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6307. Min Act: -0.1700
Data Index: 275866 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.5994. Min Act: -0.1700
Data Index: 122034 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.5994. Min Act: -0.1700
Data Index: 2216053 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19