Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1745 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.9581. Min Act: -0.1700
Data Index: 2862846 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.9423. Min Act: -0.1700
Data Index: 6466197 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.9423. Min Act: -0.1700
Data Index: 8514749 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.9106. Min Act: -0.1700
Data Index: 1215940 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8789. Min Act: -0.1700
Data Index: 5423249 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8789. Min Act: -0.1700
Data Index: 3577963 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8789. Min Act: -0.1700
Data Index: 4243116 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8789. Min Act: -0.1700
Data Index: 3256266 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8630. Min Act: -0.1700
Data Index: 4190132 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8630. Min Act: -0.1700
Data Index: 5780308 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8312. Min Act: -0.1700
Data Index: 4385943 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8471. Min Act: -0.1700
Data Index: 5820105 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8630. Min Act: -0.1700
Data Index: 422934 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8312. Min Act: -0.1700
Data Index: 1531234 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8471. Min Act: -0.1700
Data Index: 4649417 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.8312. Min Act: -0.1700
Data Index: 2986563 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.7994. Min Act: -0.1700
Data Index: 1878840 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.7994. Min Act: -0.1700
Data Index: 2539725 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.7675. Min Act: -0.1700
Data Index: 4004703 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9581. Min Range: -2.9581
Max Act: 2.7834. Min Act: -0.1700
Data Index: 573025 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19