Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4523 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.6900. Min Act: -0.1700
Data Index: 4051358 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.5650. Min Act: -0.1700
Data Index: 8827024 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.5025. Min Act: -0.1700
Data Index: 708526 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.2525. Min Act: -0.1700
Data Index: 8113371 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.2525. Min Act: -0.1700
Data Index: 5313702 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.1900. Min Act: -0.1700
Data Index: 7514660 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.1587. Min Act: -0.1700
Data Index: 5297768 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.0650. Min Act: -0.1700
Data Index: 8691424 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.0337. Min Act: -0.1700
Data Index: 1310210 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.0337. Min Act: -0.1700
Data Index: 5805368 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.0337. Min Act: -0.1700
Data Index: 4675465 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.0025. Min Act: -0.1700
Data Index: 4817174 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6900. Min Range: -8.6900
Max Act: 8.0025. Min Act: -0.1700
Data Index: 1469091 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6900. Min Range: -8.6900
Max Act: 7.9712. Min Act: -0.1700
Data Index: 2258112 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6900. Min Range: -8.6900
Max Act: 7.9400. Min Act: -0.1700
Data Index: 3592180 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6900. Min Range: -8.6900
Max Act: 7.9400. Min Act: -0.1700
Data Index: 4547846 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6900. Min Range: -8.6900
Max Act: 7.9087. Min Act: -0.1700
Data Index: 3743991 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6900. Min Range: -8.6900
Max Act: 7.9087. Min Act: -0.1700
Data Index: 5824246 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6900. Min Range: -8.6900
Max Act: 7.9400. Min Act: -0.1700
Data Index: 7765718 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6900. Min Range: -8.6900
Max Act: 7.8775. Min Act: -0.1700
Data Index: 4028828 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19