Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.3598. Min Act: -0.1700
Data Index: 6097320 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.2973. Min Act: -0.1700
Data Index: 4107476 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.2036. Min Act: -0.1700
Data Index: 7817728 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.1411. Min Act: -0.1700
Data Index: 8210168 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.1411. Min Act: -0.1700
Data Index: 1097874 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0161. Min Act: -0.1700
Data Index: 1333102 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0161. Min Act: -0.1700
Data Index: 8672495 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0786. Min Act: -0.1700
Data Index: 2716343 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0473. Min Act: -0.1700
Data Index: 1447684 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0161. Min Act: -0.1700
Data Index: 2136208 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0161. Min Act: -0.1700
Data Index: 1480243 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0161. Min Act: -0.1700
Data Index: 7335981 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3598. Min Range: -7.3598
Max Act: 6.9848. Min Act: -0.1700
Data Index: 3580903 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3598. Min Range: -7.3598
Max Act: 6.9536. Min Act: -0.1700
Data Index: 1646010 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3598. Min Range: -7.3598
Max Act: 7.0161. Min Act: -0.1700
Data Index: 7627062 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3598. Min Range: -7.3598
Max Act: 6.9536. Min Act: -0.1700
Data Index: 8079704 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3598. Min Range: -7.3598
Max Act: 6.9536. Min Act: -0.1700
Data Index: 3241347 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3598. Min Range: -7.3598
Max Act: 6.9536. Min Act: -0.1700
Data Index: 5682425 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3598. Min Range: -7.3598
Max Act: 6.9536. Min Act: -0.1700
Data Index: 4080927 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3598. Min Range: -7.3598
Max Act: 6.9536. Min Act: -0.1700
Data Index: 3293293 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19