Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5336 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1796. Min Range: -6.1796
Max Act: 6.1796. Min Act: -0.1700
Data Index: 2348935 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1796. Min Range: -6.1796
Max Act: 6.0233. Min Act: -0.1700
Data Index: 7109467 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1796. Min Range: -6.1796
Max Act: 6.0233. Min Act: -0.1700
Data Index: 199218 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1796. Min Range: -6.1796
Max Act: 6.0233. Min Act: -0.1700
Data Index: 4766245 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.9921. Min Act: -0.1700
Data Index: 2951088 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.9296. Min Act: -0.1700
Data Index: 2522017 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.9608. Min Act: -0.1700
Data Index: 6108661 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.8983. Min Act: -0.1700
Data Index: 6798399 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.8983. Min Act: -0.1700
Data Index: 2326965 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.8671. Min Act: -0.1700
Data Index: 5645171 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.8358. Min Act: -0.1700
Data Index: 8765316 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.8671. Min Act: -0.1700
Data Index: 1610521 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.8358. Min Act: -0.1700
Data Index: 7610879 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.8046. Min Act: -0.1700
Data Index: 2579114 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.7733. Min Act: -0.1700
Data Index: 4923577 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.7733. Min Act: -0.1700
Data Index: 6152158 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.7108. Min Act: -0.1700
Data Index: 2579110 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.7733. Min Act: -0.1700
Data Index: 7513379 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.7421. Min Act: -0.1700
Data Index: 745165 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1796. Min Range: -6.1796
Max Act: 5.7421. Min Act: -0.1700
Data Index: 4330919 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19