Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2145 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.9248. Min Act: -0.1700
Data Index: 3443932 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.6123. Min Act: -0.1700
Data Index: 2701088 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.6123. Min Act: -0.1700
Data Index: 4942097 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.4248. Min Act: -0.1700
Data Index: 7897120 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.3936. Min Act: -0.1700
Data Index: 1516316 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4275725 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4275727 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2686. Min Act: -0.1700
Data Index: 5649320 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2998. Min Act: -0.1700
Data Index: 11576 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2998. Min Act: -0.1700
Data Index: 1975725 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2373. Min Act: -0.1700
Data Index: 91261 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2373. Min Act: -0.1700
Data Index: 1240033 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4513873 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2686. Min Act: -0.1700
Data Index: 6262970 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2373. Min Act: -0.1700
Data Index: 4350856 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2061. Min Act: -0.1700
Data Index: 5631547 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.1748. Min Act: -0.1700
Data Index: 4275728 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2373. Min Act: -0.1700
Data Index: 756340 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.2061. Min Act: -0.1700
Data Index: 5630525 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9248. Min Range: -5.9248
Max Act: 5.1748. Min Act: -0.1700
Data Index: 4975470 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19