Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2803. Min Range: -7.2803
Max Act: 7.2803. Min Act: -0.1700
Data Index: 2882083 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2803. Min Range: -7.2803
Max Act: 7.2178. Min Act: -0.1700
Data Index: 7467169 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2803. Min Range: -7.2803
Max Act: 7.1865. Min Act: -0.1700
Data Index: 6217297 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2803. Min Range: -7.2803
Max Act: 7.1553. Min Act: -0.1700
Data Index: 7568315 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2803. Min Range: -7.2803
Max Act: 7.0615. Min Act: -0.1700
Data Index: 8133752 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2803. Min Range: -7.2803
Max Act: 7.0615. Min Act: -0.1700
Data Index: 8196857 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2803. Min Range: -7.2803
Max Act: 7.0303. Min Act: -0.1700
Data Index: 7281453 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9990. Min Act: -0.1700
Data Index: 5515293 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9990. Min Act: -0.1700
Data Index: 4134901 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9365. Min Act: -0.1700
Data Index: 29871 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9365. Min Act: -0.1700
Data Index: 8064840 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9365. Min Act: -0.1700
Data Index: 1791090 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9053. Min Act: -0.1700
Data Index: 4434104 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9053. Min Act: -0.1700
Data Index: 7803479 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.9053. Min Act: -0.1700
Data Index: 1620241 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.8740. Min Act: -0.1700
Data Index: 5250130 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.8428. Min Act: -0.1700
Data Index: 1631830 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.8428. Min Act: -0.1700
Data Index: 6271887 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.8115. Min Act: -0.1700
Data Index: 8160280 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2803. Min Range: -7.2803
Max Act: 6.8115. Min Act: -0.1700
Data Index: 4695332 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19