Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0827. Min Range: -5.0827
Max Act: 5.0827. Min Act: -0.1700
Data Index: 4493854 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0827. Min Range: -5.0827
Max Act: 5.0515. Min Act: -0.1700
Data Index: 269730 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.9890. Min Act: -0.1700
Data Index: 6304101 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.9265. Min Act: -0.1700
Data Index: 188239 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8952. Min Act: -0.1700
Data Index: 8011605 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8952. Min Act: -0.1700
Data Index: 8488995 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8640. Min Act: -0.1700
Data Index: 5334759 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8640. Min Act: -0.1700
Data Index: 5451835 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8327. Min Act: -0.1700
Data Index: 4818903 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8327. Min Act: -0.1700
Data Index: 1917017 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8327. Min Act: -0.1700
Data Index: 6627178 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.8015. Min Act: -0.1700
Data Index: 1500577 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7702. Min Act: -0.1700
Data Index: 7983819 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7702. Min Act: -0.1700
Data Index: 437303 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7702. Min Act: -0.1700
Data Index: 3969972 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7390. Min Act: -0.1700
Data Index: 8537319 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7390. Min Act: -0.1700
Data Index: 8173515 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7077. Min Act: -0.1700
Data Index: 7553981 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7077. Min Act: -0.1700
Data Index: 570298 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0827. Min Range: -5.0827
Max Act: 4.7077. Min Act: -0.1700
Data Index: 7697438 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19