Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 440 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.6264. Min Act: -0.1700
Data Index: 4995402 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.5620. Min Act: -0.1700
Data Index: 986419 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.5620. Min Act: -0.1700
Data Index: 1340889 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.5781. Min Act: -0.1700
Data Index: 3148344 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.5458. Min Act: -0.1700
Data Index: 7864718 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.5458. Min Act: -0.1700
Data Index: 8333561 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.5297. Min Act: -0.1700
Data Index: 1449742 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.5135. Min Act: -0.1700
Data Index: 6950392 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4973. Min Act: -0.1700
Data Index: 8149447 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4811. Min Act: -0.1700
Data Index: 3842782 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4811. Min Act: -0.1700
Data Index: 6758266 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4811. Min Act: -0.1700
Data Index: 4927960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4649. Min Act: -0.1700
Data Index: 7879215 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4649. Min Act: -0.1700
Data Index: 4023597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4811. Min Act: -0.1700
Data Index: 2775200 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4649. Min Act: -0.1700
Data Index: 829123 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4486. Min Act: -0.1700
Data Index: 6071350 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4160. Min Act: -0.1700
Data Index: 2519537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4486. Min Act: -0.1700
Data Index: 6831785 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6264. Min Range: -2.6264
Max Act: 2.4323. Min Act: -0.1700
Data Index: 2172448 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19