Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2556 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3988. Min Act: -0.1700
Data Index: 2080119 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3988. Min Act: -0.1700
Data Index: 3286969 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3675. Min Act: -0.1700
Data Index: 8548656 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3675. Min Act: -0.1700
Data Index: 3672222 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3363. Min Act: -0.1700
Data Index: 4377731 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3363. Min Act: -0.1700
Data Index: 7138478 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3050. Min Act: -0.1700
Data Index: 3943581 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.3050. Min Act: -0.1700
Data Index: 4394440 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2738. Min Act: -0.1700
Data Index: 6170607 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2425. Min Act: -0.1700
Data Index: 4851373 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2425. Min Act: -0.1700
Data Index: 1565566 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2425. Min Act: -0.1700
Data Index: 8501719 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2113. Min Act: -0.1700
Data Index: 1857310 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2113. Min Act: -0.1700
Data Index: 3930578 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2113. Min Act: -0.1700
Data Index: 6891494 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2113. Min Act: -0.1700
Data Index: 7019773 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2113. Min Act: -0.1700
Data Index: 2941205 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2113. Min Act: -0.1700
Data Index: 5336655 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2425. Min Act: -0.1700
Data Index: 140013 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3988. Min Range: -4.3988
Max Act: 4.2113. Min Act: -0.1700
Data Index: 7339858 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19