Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.4709. Min Act: -0.1700
Data Index: 6753725 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.3771. Min Act: -0.1700
Data Index: 2191932 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.3771. Min Act: -0.1700
Data Index: 6116087 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.3146. Min Act: -0.1700
Data Index: 4852021 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.3146. Min Act: -0.1700
Data Index: 7088578 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.2521. Min Act: -0.1700
Data Index: 3410607 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.2209. Min Act: -0.1700
Data Index: 7901261 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1896. Min Act: -0.1700
Data Index: 2686520 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1896. Min Act: -0.1700
Data Index: 6460134 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1896. Min Act: -0.1700
Data Index: 544831 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1896. Min Act: -0.1700
Data Index: 6012577 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1584. Min Act: -0.1700
Data Index: 2315982 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1896. Min Act: -0.1700
Data Index: 158768 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1584. Min Act: -0.1700
Data Index: 7254661 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1584. Min Act: -0.1700
Data Index: 4302108 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1271. Min Act: -0.1700
Data Index: 2176201 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1271. Min Act: -0.1700
Data Index: 4346621 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1271. Min Act: -0.1700
Data Index: 5219152 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.1584. Min Act: -0.1700
Data Index: 3228460 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4709. Min Range: -5.4709
Max Act: 5.0959. Min Act: -0.1700
Data Index: 1019785 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19