Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7538. Min Act: -0.1700
Data Index: 3879345 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.6288. Min Act: -0.1699
Data Index: 2187226 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5663. Min Act: -0.1700
Data Index: 7471035 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4726. Min Act: -0.1700
Data Index: 2553485 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4726. Min Act: -0.1700
Data Index: 4548184 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4726. Min Act: -0.1700
Data Index: 3532815 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4726. Min Act: -0.1700
Data Index: 1895077 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4726. Min Act: -0.1700
Data Index: 7743859 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4413. Min Act: -0.1700
Data Index: 3125068 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4413. Min Act: -0.1700
Data Index: 7876808 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4101. Min Act: -0.1700
Data Index: 1628872 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4101. Min Act: -0.1700
Data Index: 242710 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4101. Min Act: -0.1700
Data Index: 1142942 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4101. Min Act: -0.1700
Data Index: 4723997 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4101. Min Act: -0.1700
Data Index: 6048770 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3788. Min Act: -0.1700
Data Index: 3603716 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3788. Min Act: -0.1700
Data Index: 2759305 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3788. Min Act: -0.1700
Data Index: 4817729 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3788. Min Act: -0.1700
Data Index: 5631498 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3788. Min Act: -0.1700
Data Index: 439912 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19