Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1628 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0046. Min Range: -5.0046
Max Act: 5.0046. Min Act: -0.1700
Data Index: 1375056 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.9108. Min Act: -0.1700
Data Index: 2021298 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.9108. Min Act: -0.1700
Data Index: 1007657 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.9108. Min Act: -0.1700
Data Index: 3612736 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.9108. Min Act: -0.1700
Data Index: 7664052 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8796. Min Act: -0.1700
Data Index: 84742 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.9108. Min Act: -0.1700
Data Index: 7148170 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8483. Min Act: -0.1700
Data Index: 623986 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8796. Min Act: -0.1700
Data Index: 5795996 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8483. Min Act: -0.1700
Data Index: 5539876 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8171. Min Act: -0.1700
Data Index: 2382994 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8483. Min Act: -0.1700
Data Index: 5065159 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8483. Min Act: -0.1700
Data Index: 809848 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8483. Min Act: -0.1700
Data Index: 8282712 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8171. Min Act: -0.1700
Data Index: 225821 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.7858. Min Act: -0.1700
Data Index: 2334162 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.7858. Min Act: -0.1700
Data Index: 877506 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8171. Min Act: -0.1700
Data Index: 6823327 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8483. Min Act: -0.1700
Data Index: 1457020 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0046. Min Range: -5.0046
Max Act: 4.8171. Min Act: -0.1700
Data Index: 2645230 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19