Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2402. Min Range: -8.2402
Max Act: 8.2402. Min Act: -0.1700
Data Index: 2000627 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.9902. Min Act: -0.1700
Data Index: 5388010 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.9902. Min Act: -0.1700
Data Index: 520910 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.9277. Min Act: -0.1700
Data Index: 706074 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8964. Min Act: -0.1700
Data Index: 6618124 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.9277. Min Act: -0.1700
Data Index: 6332969 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.9277. Min Act: -0.1700
Data Index: 8740764 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.9277. Min Act: -0.1700
Data Index: 4746550 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8964. Min Act: -0.1700
Data Index: 2142325 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8964. Min Act: -0.1700
Data Index: 706087 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8339. Min Act: -0.1700
Data Index: 867633 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8652. Min Act: -0.1700
Data Index: 2339084 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8964. Min Act: -0.1700
Data Index: 8003567 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8027. Min Act: -0.1700
Data Index: 38513 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8339. Min Act: -0.1700
Data Index: 520931 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8339. Min Act: -0.1700
Data Index: 8648174 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8339. Min Act: -0.1700
Data Index: 1024067 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8339. Min Act: -0.1700
Data Index: 2061765 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8027. Min Act: -0.1700
Data Index: 706067 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2402. Min Range: -8.2402
Max Act: 7.8027. Min Act: -0.1700
Data Index: 5625868 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19