Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.6666. Min Act: -0.1700
Data Index: 6894681 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.6505. Min Act: -0.1700
Data Index: 5632220 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.6023. Min Act: -0.1700
Data Index: 1370197 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5862. Min Act: -0.1700
Data Index: 2210026 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5862. Min Act: -0.1700
Data Index: 2269302 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5540. Min Act: -0.1700
Data Index: 7599372 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5216. Min Act: -0.1700
Data Index: 462241 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5378. Min Act: -0.1700
Data Index: 1135057 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5055. Min Act: -0.1700
Data Index: 8464233 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5055. Min Act: -0.1700
Data Index: 2317569 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5216. Min Act: -0.1700
Data Index: 8115780 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5055. Min Act: -0.1700
Data Index: 8488920 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.5055. Min Act: -0.1700
Data Index: 2009174 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.4893. Min Act: -0.1700
Data Index: 4603369 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.4730. Min Act: -0.1700
Data Index: 2367220 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.4893. Min Act: -0.1700
Data Index: 6586303 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.4730. Min Act: -0.1700
Data Index: 7074635 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.4730. Min Act: -0.1700
Data Index: 3311478 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.4568. Min Act: -0.1700
Data Index: 4062023 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6666. Min Range: -2.6666
Max Act: 2.4568. Min Act: -0.1700
Data Index: 6629748 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19