Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2603. Min Range: -6.2603
Max Act: 6.2603. Min Act: -0.1700
Data Index: 2284371 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2603. Min Range: -6.2603
Max Act: 6.0103. Min Act: -0.1700
Data Index: 4179616 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.8853. Min Act: -0.1700
Data Index: 1128155 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.8540. Min Act: -0.1700
Data Index: 1431778 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.8228. Min Act: -0.1700
Data Index: 6802295 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.6978. Min Act: -0.1700
Data Index: 5453527 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.6978. Min Act: -0.1700
Data Index: 5153604 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.6353. Min Act: -0.1700
Data Index: 2024150 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.6978. Min Act: -0.1700
Data Index: 1611064 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.6665. Min Act: -0.1700
Data Index: 4824584 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.6040. Min Act: -0.1700
Data Index: 3484316 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.6040. Min Act: -0.1700
Data Index: 1486500 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5728. Min Act: -0.1700
Data Index: 3848986 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5728. Min Act: -0.1700
Data Index: 8120284 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5728. Min Act: -0.1700
Data Index: 6875735 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5728. Min Act: -0.1700
Data Index: 8710823 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5103. Min Act: -0.1700
Data Index: 12417 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5103. Min Act: -0.1700
Data Index: 6685158 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5103. Min Act: -0.1700
Data Index: 3009468 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2603. Min Range: -6.2603
Max Act: 5.5728. Min Act: -0.1700
Data Index: 5588372 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19