Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1951 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.5162. Min Act: -0.1700
Data Index: 7296358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.5162. Min Act: -0.1700
Data Index: 1657076 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.5162. Min Act: -0.1700
Data Index: 4634652 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.4225. Min Act: -0.1700
Data Index: 8012645 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.3600. Min Act: -0.1700
Data Index: 5533030 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.3287. Min Act: -0.1700
Data Index: 8300473 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.3600. Min Act: -0.1700
Data Index: 6341522 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2662. Min Act: -0.1700
Data Index: 8612715 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2350. Min Act: -0.1700
Data Index: 3737998 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2662. Min Act: -0.1700
Data Index: 4305738 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2350. Min Act: -0.1700
Data Index: 5837593 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2350. Min Act: -0.1700
Data Index: 8687042 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2662. Min Act: -0.1700
Data Index: 3803115 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2350. Min Act: -0.1700
Data Index: 3400129 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2037. Min Act: -0.1700
Data Index: 6395230 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.1725. Min Act: -0.1700
Data Index: 7789023 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.2037. Min Act: -0.1700
Data Index: 2805204 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.1412. Min Act: -0.1700
Data Index: 7959773 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.1412. Min Act: -0.1700
Data Index: 3870260 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5162. Min Range: -5.5162
Max Act: 5.1412. Min Act: -0.1700
Data Index: 916672 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19