Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3335. Min Range: -6.3335
Max Act: 6.3023. Min Act: -0.1700
Data Index: 4541449 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3335. Min Range: -6.3335
Max Act: 6.3335. Min Act: -0.1700
Data Index: 8381182 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.9898. Min Act: -0.1700
Data Index: 1046149 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.9585. Min Act: -0.1700
Data Index: 5260373 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.9273. Min Act: -0.1700
Data Index: 3858713 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8960. Min Act: -0.1700
Data Index: 3295521 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8960. Min Act: -0.1700
Data Index: 7889481 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8960. Min Act: -0.1700
Data Index: 281760 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8648. Min Act: -0.1700
Data Index: 6722564 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8648. Min Act: -0.1700
Data Index: 7679021 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8335. Min Act: -0.1700
Data Index: 7316128 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8335. Min Act: -0.1700
Data Index: 2119677 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8023. Min Act: -0.1700
Data Index: 3130778 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8023. Min Act: -0.1700
Data Index: 7639660 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8023. Min Act: -0.1700
Data Index: 7270061 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8023. Min Act: -0.1700
Data Index: 4667153 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8023. Min Act: -0.1700
Data Index: 4723176 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.8023. Min Act: -0.1700
Data Index: 508731 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.7710. Min Act: -0.1700
Data Index: 5263011 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3335. Min Range: -6.3335
Max Act: 5.7710. Min Act: -0.1700
Data Index: 5770740 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19