Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5024 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2647. Min Range: -6.2647
Max Act: 6.2647. Min Act: -0.1700
Data Index: 6309471 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2647. Min Range: -6.2647
Max Act: 6.1085. Min Act: -0.1700
Data Index: 4022924 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2647. Min Range: -6.2647
Max Act: 6.0147. Min Act: -0.1700
Data Index: 5756265 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.9522. Min Act: -0.1700
Data Index: 6560521 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.9210. Min Act: -0.1700
Data Index: 4359756 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.9210. Min Act: -0.1700
Data Index: 1168016 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.8272. Min Act: -0.1700
Data Index: 5689706 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.7960. Min Act: -0.1700
Data Index: 2929962 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.7647. Min Act: -0.1700
Data Index: 6622920 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.7647. Min Act: -0.1700
Data Index: 685083 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.7335. Min Act: -0.1700
Data Index: 1213034 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.7022. Min Act: -0.1700
Data Index: 5856747 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.6710. Min Act: -0.1700
Data Index: 5006208 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.7022. Min Act: -0.1700
Data Index: 887679 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.6085. Min Act: -0.1700
Data Index: 857825 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.6710. Min Act: -0.1700
Data Index: 8084643 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.6085. Min Act: -0.1700
Data Index: 481383 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.5460. Min Act: -0.1700
Data Index: 2654257 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.5772. Min Act: -0.1700
Data Index: 6207832 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2647. Min Range: -6.2647
Max Act: 5.5772. Min Act: -0.1700
Data Index: 5878496 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19