Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.5586. Min Act: -0.1700
Data Index: 8556123 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.5274. Min Act: -0.1700
Data Index: 5717851 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.5586. Min Act: -0.1700
Data Index: 5565354 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4961. Min Act: -0.1700
Data Index: 1074577 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4961. Min Act: -0.1700
Data Index: 2596920 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4961. Min Act: -0.1700
Data Index: 8038676 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4961. Min Act: -0.1700
Data Index: 4086531 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4961. Min Act: -0.1700
Data Index: 1966695 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4649. Min Act: -0.1700
Data Index: 2673014 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4649. Min Act: -0.1700
Data Index: 8764596 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4024. Min Act: -0.1700
Data Index: 6485220 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3711. Min Act: -0.1700
Data Index: 6626834 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.4024. Min Act: -0.1700
Data Index: 7053017 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3711. Min Act: -0.1700
Data Index: 1316492 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3711. Min Act: -0.1700
Data Index: 5663109 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3711. Min Act: -0.1700
Data Index: 4050234 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3711. Min Act: -0.1700
Data Index: 1316503 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3399. Min Act: -0.1700
Data Index: 4951610 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3399. Min Act: -0.1700
Data Index: 7762421 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5586. Min Range: -5.5586
Max Act: 5.3399. Min Act: -0.1700
Data Index: 6404958 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19