Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.8411. Min Act: -0.1700
Data Index: 3656266 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.8093. Min Act: -0.1700
Data Index: 7664943 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7934. Min Act: -0.1700
Data Index: 937587 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7934. Min Act: -0.1700
Data Index: 529907 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7934. Min Act: -0.1700
Data Index: 7396130 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7934. Min Act: -0.1700
Data Index: 5159190 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7775. Min Act: -0.1700
Data Index: 5882412 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7775. Min Act: -0.1700
Data Index: 1851903 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7775. Min Act: -0.1700
Data Index: 4997423 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7934. Min Act: -0.1700
Data Index: 2925738 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7775. Min Act: -0.1700
Data Index: 3554747 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7775. Min Act: -0.1700
Data Index: 2977833 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 308819 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 4970418 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 756669 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 7032402 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7615. Min Act: -0.1700
Data Index: 1736644 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 201117 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 5159189 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8411. Min Range: -2.8411
Max Act: 2.7456. Min Act: -0.1700
Data Index: 1679371 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19