Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.9692. Min Act: -0.1700
Data Index: 6763231 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.8442. Min Act: -0.1700
Data Index: 3362005 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.8442. Min Act: -0.1700
Data Index: 7055305 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.8130. Min Act: -0.1700
Data Index: 1143871 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4518375 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.7817. Min Act: -0.1700
Data Index: 8713454 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.7192. Min Act: -0.1700
Data Index: 569455 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6879. Min Act: -0.1700
Data Index: 402009 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6879. Min Act: -0.1700
Data Index: 6832726 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6567. Min Act: -0.1700
Data Index: 2913182 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6567. Min Act: -0.1700
Data Index: 5379615 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6567. Min Act: -0.1700
Data Index: 5835478 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6567. Min Act: -0.1700
Data Index: 3488747 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6254. Min Act: -0.1700
Data Index: 572130 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.5942. Min Act: -0.1700
Data Index: 5477896 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6254. Min Act: -0.1700
Data Index: 5121666 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.6254. Min Act: -0.1700
Data Index: 709077 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.5942. Min Act: -0.1700
Data Index: 369826 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.5942. Min Act: -0.1700
Data Index: 4890646 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9692. Min Range: -4.9692
Max Act: 4.5942. Min Act: -0.1700
Data Index: 259427 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19