Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2711. Min Range: -5.2711
Max Act: 5.2711. Min Act: -0.1700
Data Index: 1051282 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.7398. Min Act: -0.1700
Data Index: 5852925 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.7086. Min Act: -0.1700
Data Index: 6395217 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.7398. Min Act: -0.1700
Data Index: 4180857 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.7086. Min Act: -0.1700
Data Index: 2762571 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.7398. Min Act: -0.1700
Data Index: 5006208 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6773. Min Act: -0.1700
Data Index: 6611946 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6773. Min Act: -0.1700
Data Index: 2653716 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6461. Min Act: -0.1700
Data Index: 470603 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6773. Min Act: -0.1700
Data Index: 5318566 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6461. Min Act: -0.1700
Data Index: 4015944 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6148. Min Act: -0.1700
Data Index: 2667996 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6148. Min Act: -0.1700
Data Index: 118193 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.5836. Min Act: -0.1700
Data Index: 8262669 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.5523. Min Act: -0.1700
Data Index: 7842247 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.6461. Min Act: -0.1700
Data Index: 4709009 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.5523. Min Act: -0.1700
Data Index: 249948 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.4898. Min Act: -0.1700
Data Index: 8802292 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.5211. Min Act: -0.1700
Data Index: 8041106 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2711. Min Range: -5.2711
Max Act: 4.5211. Min Act: -0.1700
Data Index: 5354651 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19