Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0662. Min Range: -4.0662
Max Act: 4.0662. Min Act: -0.1700
Data Index: 3359414 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.9412. Min Act: -0.1700
Data Index: 2563985 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.9412. Min Act: -0.1700
Data Index: 3467677 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.8318. Min Act: -0.1700
Data Index: 7154943 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.8161. Min Act: -0.1700
Data Index: 1010198 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.8161. Min Act: -0.1700
Data Index: 4136363 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.8161. Min Act: -0.1700
Data Index: 2563986 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.8318. Min Act: -0.1700
Data Index: 1919889 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7848. Min Act: -0.1700
Data Index: 1985264 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7848. Min Act: -0.1700
Data Index: 7829766 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7848. Min Act: -0.1700
Data Index: 6385032 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7848. Min Act: -0.1700
Data Index: 2251422 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7692. Min Act: -0.1700
Data Index: 4531417 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7379. Min Act: -0.1700
Data Index: 5883075 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7692. Min Act: -0.1700
Data Index: 7101838 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7692. Min Act: -0.1700
Data Index: 3988079 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7536. Min Act: -0.1700
Data Index: 7696554 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7379. Min Act: -0.1700
Data Index: 7864755 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7536. Min Act: -0.1700
Data Index: 2891351 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0662. Min Range: -4.0662
Max Act: 3.7536. Min Act: -0.1700
Data Index: 6573452 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19