Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4568 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.5467. Min Act: -0.1700
Data Index: 4685536 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.3905. Min Act: -0.1700
Data Index: 6529439 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.3592. Min Act: -0.1700
Data Index: 3507764 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.3280. Min Act: -0.1700
Data Index: 4765671 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2967. Min Act: -0.1700
Data Index: 445918 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2967. Min Act: -0.1700
Data Index: 6529440 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2967. Min Act: -0.1700
Data Index: 4562241 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2967. Min Act: -0.1700
Data Index: 5253902 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2655. Min Act: -0.1700
Data Index: 2592528 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2655. Min Act: -0.1700
Data Index: 6529438 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2342. Min Act: -0.1700
Data Index: 6321592 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2030. Min Act: -0.1700
Data Index: 5921139 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2030. Min Act: -0.1700
Data Index: 6529437 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.2030. Min Act: -0.1700
Data Index: 3384920 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.1717. Min Act: -0.1700
Data Index: 253118 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.1405. Min Act: -0.1700
Data Index: 5018301 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.1092. Min Act: -0.1700
Data Index: 7177532 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.1092. Min Act: -0.1700
Data Index: 6157287 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.1092. Min Act: -0.1700
Data Index: 99360 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5467. Min Range: -5.5467
Max Act: 5.1092. Min Act: -0.1700
Data Index: 4685534 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19