Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.9796. Min Act: -0.1700
Data Index: 6698947 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.6359. Min Act: -0.1700
Data Index: 1804449 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.6046. Min Act: -0.1700
Data Index: 4963237 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.5734. Min Act: -0.1700
Data Index: 5220879 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.5109. Min Act: -0.1700
Data Index: 359798 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.5109. Min Act: -0.1700
Data Index: 5711806 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4796. Min Act: -0.1700
Data Index: 5681530 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4171. Min Act: -0.1700
Data Index: 6354515 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4171. Min Act: -0.1700
Data Index: 6020737 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3859. Min Act: -0.1700
Data Index: 2608411 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3859. Min Act: -0.1700
Data Index: 8624356 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3859. Min Act: -0.1700
Data Index: 4746459 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3546. Min Act: -0.1700
Data Index: 621829 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3234. Min Act: -0.1700
Data Index: 8358995 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3234. Min Act: -0.1700
Data Index: 6382161 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3234. Min Act: -0.1700
Data Index: 4398598 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3234. Min Act: -0.1700
Data Index: 7037734 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3234. Min Act: -0.1700
Data Index: 3618930 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.2609. Min Act: -0.1700
Data Index: 8184329 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.2296. Min Act: -0.1700
Data Index: 7882615 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19