Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.7327. Min Act: -0.1700
Data Index: 884733 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.6858. Min Act: -0.1700
Data Index: 8828935 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.6858. Min Act: -0.1700
Data Index: 193905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.6232. Min Act: -0.1700
Data Index: 3323913 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.6076. Min Act: -0.1700
Data Index: 7804474 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.5919. Min Act: -0.1700
Data Index: 4698098 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.5606. Min Act: -0.1700
Data Index: 4838954 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.5450. Min Act: -0.1700
Data Index: 2194009 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.5450. Min Act: -0.1700
Data Index: 554797 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.5136. Min Act: -0.1700
Data Index: 3098962 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.5293. Min Act: -0.1700
Data Index: 4694368 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4980. Min Act: -0.1700
Data Index: 6021554 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4980. Min Act: -0.1700
Data Index: 8328217 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4980. Min Act: -0.1700
Data Index: 7101848 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4980. Min Act: -0.1700
Data Index: 1193538 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4667. Min Act: -0.1700
Data Index: 4901067 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4823. Min Act: -0.1700
Data Index: 7101847 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4510. Min Act: -0.1700
Data Index: 1652960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4510. Min Act: -0.1700
Data Index: 2464538 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7327. Min Range: -3.7327
Max Act: 3.4667. Min Act: -0.1700
Data Index: 8201089 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19