Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.4159. Min Act: -0.1700
Data Index: 2296566 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.2284. Min Act: -0.1700
Data Index: 3019242 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.1659. Min Act: -0.1700
Data Index: 2615315 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.1659. Min Act: -0.1700
Data Index: 3199412 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.1034. Min Act: -0.1699
Data Index: 3464376 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.1659. Min Act: -0.1700
Data Index: 6819725 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.0409. Min Act: -0.1700
Data Index: 8645682 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.0409. Min Act: -0.1700
Data Index: 2751233 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.0409. Min Act: -0.1700
Data Index: 8130997 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.0409. Min Act: -0.1700
Data Index: 6801017 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4159. Min Range: -10.4159
Max Act: 10.0409. Min Act: -0.1700
Data Index: 20929 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.9784. Min Act: -0.1700
Data Index: 8055390 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.8534. Min Act: -0.1700
Data Index: 565019 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.8534. Min Act: -0.1700
Data Index: 6211217 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.8534. Min Act: -0.1700
Data Index: 4127147 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.9159. Min Act: -0.1700
Data Index: 5147846 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.7909. Min Act: -0.1700
Data Index: 1595578 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.7909. Min Act: -0.1698
Data Index: 3584057 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.7909. Min Act: -0.1700
Data Index: 2583550 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4159. Min Range: -10.4159
Max Act: 9.7284. Min Act: -0.1699
Data Index: 1929911 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19