Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.6400. Min Act: -0.1700
Data Index: 3660511 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.5462. Min Act: -0.1700
Data Index: 2025571 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.4525. Min Act: -0.1700
Data Index: 2298719 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.3587. Min Act: -0.1700
Data Index: 4652761 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.3275. Min Act: -0.1700
Data Index: 1385587 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.3275. Min Act: -0.1700
Data Index: 3155692 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2962. Min Act: -0.1700
Data Index: 5866440 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2962. Min Act: -0.1700
Data Index: 4522481 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2650. Min Act: -0.1700
Data Index: 2623244 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2337. Min Act: -0.1700
Data Index: 5079211 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2337. Min Act: -0.1700
Data Index: 4647994 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2650. Min Act: -0.1700
Data Index: 8085610 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2337. Min Act: -0.1700
Data Index: 3136529 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.1712. Min Act: -0.1700
Data Index: 1302115 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2025. Min Act: -0.1700
Data Index: 2802751 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7575652 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7450251 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.1712. Min Act: -0.1700
Data Index: 620273 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7883694 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6400. Min Range: -5.6400
Max Act: 5.2025. Min Act: -0.1700
Data Index: 201032 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19