Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.9347. Min Act: -0.1700
Data Index: 8462746 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.9347. Min Act: -0.1700
Data Index: 2762012 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.7159. Min Act: -0.1700
Data Index: 966141 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.6847. Min Act: -0.1700
Data Index: 7423787 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.6534. Min Act: -0.1700
Data Index: 193354 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.6534. Min Act: -0.1700
Data Index: 4786656 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.6222. Min Act: -0.1700
Data Index: 6805312 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.5909. Min Act: -0.1700
Data Index: 3968520 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4972. Min Act: -0.1700
Data Index: 1901092 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.5284. Min Act: -0.1700
Data Index: 1141858 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4659. Min Act: -0.1700
Data Index: 3064410 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4972. Min Act: -0.1700
Data Index: 3271785 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4972. Min Act: -0.1700
Data Index: 4653195 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4972. Min Act: -0.1700
Data Index: 4051485 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4972. Min Act: -0.1700
Data Index: 7460529 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4972. Min Act: -0.1700
Data Index: 8562883 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4659. Min Act: -0.1700
Data Index: 4435211 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4347. Min Act: -0.1700
Data Index: 4441067 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4659. Min Act: -0.1700
Data Index: 4098021 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9347. Min Range: -5.9347
Max Act: 5.4659. Min Act: -0.1700
Data Index: 7918768 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19