Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3995 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.3497. Min Act: -0.1700
Data Index: 4254936 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.2247. Min Act: -0.1700
Data Index: 7689267 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.1622. Min Act: -0.1700
Data Index: 6326579 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.1622. Min Act: -0.1700
Data Index: 7032506 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.1622. Min Act: -0.1700
Data Index: 489037 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.1622. Min Act: -0.1700
Data Index: 162042 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.1622. Min Act: -0.1700
Data Index: 6287471 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0684. Min Act: -0.1700
Data Index: 3394889 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0372. Min Act: -0.1700
Data Index: 5916463 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0372. Min Act: -0.1700
Data Index: 632802 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0372. Min Act: -0.1700
Data Index: 2353120 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0372. Min Act: -0.1700
Data Index: 7561939 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3497. Min Range: -7.3497
Max Act: 6.9747. Min Act: -0.1700
Data Index: 4826761 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0059. Min Act: -0.1700
Data Index: 8075927 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0059. Min Act: -0.1700
Data Index: 2725341 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0059. Min Act: -0.1700
Data Index: 2654804 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0059. Min Act: -0.1700
Data Index: 2654799 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3497. Min Range: -7.3497
Max Act: 7.0059. Min Act: -0.1700
Data Index: 4517237 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3497. Min Range: -7.3497
Max Act: 6.9747. Min Act: -0.1700
Data Index: 509452 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3497. Min Range: -7.3497
Max Act: 6.9747. Min Act: -0.1700
Data Index: 2548326 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19