Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4079 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.5262. Min Act: -0.1700
Data Index: 6751197 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.4950. Min Act: -0.1700
Data Index: 6228434 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.4950. Min Act: -0.1700
Data Index: 8610086 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.4637. Min Act: -0.1700
Data Index: 2488563 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.3700. Min Act: -0.1700
Data Index: 2051967 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.3700. Min Act: -0.1700
Data Index: 4908493 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.3387. Min Act: -0.1700
Data Index: 6919766 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.3387. Min Act: -0.1700
Data Index: 925689 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.3075. Min Act: -0.1700
Data Index: 3913008 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.2450. Min Act: -0.1700
Data Index: 345349 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.2450. Min Act: -0.1700
Data Index: 8142842 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.2137. Min Act: -0.1700
Data Index: 6667579 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1825. Min Act: -0.1700
Data Index: 3387417 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1825. Min Act: -0.1700
Data Index: 2805063 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1825. Min Act: -0.1700
Data Index: 5450939 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1200. Min Act: -0.1700
Data Index: 214682 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1512. Min Act: -0.1700
Data Index: 1959234 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1512. Min Act: -0.1700
Data Index: 6631907 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1200. Min Act: -0.1700
Data Index: 959346 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5262. Min Range: -5.5262
Max Act: 5.1200. Min Act: -0.1700
Data Index: 7285927 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19