Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.6892. Min Act: -0.1700
Data Index: 1071851 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.6579. Min Act: -0.1700
Data Index: 4094289 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.6267. Min Act: -0.1700
Data Index: 6032596 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5642. Min Act: -0.1700
Data Index: 8459064 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5954. Min Act: -0.1700
Data Index: 6441979 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5954. Min Act: -0.1700
Data Index: 2704783 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5642. Min Act: -0.1700
Data Index: 189526 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5017. Min Act: -0.1700
Data Index: 7502212 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5017. Min Act: -0.1700
Data Index: 8616953 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5017. Min Act: -0.1700
Data Index: 8221359 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5017. Min Act: -0.1700
Data Index: 7757390 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5017. Min Act: -0.1700
Data Index: 3671974 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5017. Min Act: -0.1700
Data Index: 6619974 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.5017. Min Act: -0.1700
Data Index: 3187257 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.4392. Min Act: -0.1700
Data Index: 4074358 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.4392. Min Act: -0.1700
Data Index: 7455006 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.4392. Min Act: -0.1700
Data Index: 561349 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.4392. Min Act: -0.1700
Data Index: 1452803 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.4079. Min Act: -0.1700
Data Index: 7070018 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.4079. Min Act: -0.1700
Data Index: 2790820 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19