Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.2403. Min Act: -0.1700
Data Index: 1344120 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.2403. Min Act: -0.1700
Data Index: 8444882 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.2246. Min Act: -0.1700
Data Index: 8406592 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.2089. Min Act: -0.1700
Data Index: 7109916 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.2089. Min Act: -0.1700
Data Index: 7109915 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1932. Min Act: -0.1700
Data Index: 2930128 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1774. Min Act: -0.1700
Data Index: 8444881 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.2089. Min Act: -0.1700
Data Index: 7523694 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1617. Min Act: -0.1700
Data Index: 4119238 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1617. Min Act: -0.1700
Data Index: 3588114 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1460. Min Act: -0.1700
Data Index: 4344155 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1145. Min Act: -0.1700
Data Index: 2599397 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1145. Min Act: -0.1700
Data Index: 7045280 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1145. Min Act: -0.1700
Data Index: 1170979 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1145. Min Act: -0.1700
Data Index: 2930129 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.1145. Min Act: -0.1700
Data Index: 8401020 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.0829. Min Act: -0.1700
Data Index: 959073 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.0987. Min Act: -0.1700
Data Index: 3588115 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.0987. Min Act: -0.1700
Data Index: 4119237 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2403. Min Range: -3.2403
Max Act: 3.0987. Min Act: -0.1700
Data Index: 7176144 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19