Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.8897. Min Act: -0.1699
Data Index: 6276138 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.4209. Min Act: -0.1700
Data Index: 8619082 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.4209. Min Act: -0.1700
Data Index: 1913566 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.3584. Min Act: -0.1700
Data Index: 1370292 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.3897. Min Act: -0.1694
Data Index: 420598 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2959. Min Act: -0.1700
Data Index: 888530 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2959. Min Act: -0.1700
Data Index: 3582061 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.3272. Min Act: -0.1700
Data Index: 7345405 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2959. Min Act: -0.1700
Data Index: 7794281 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.3272. Min Act: -0.1700
Data Index: 61711 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2959. Min Act: -0.1700
Data Index: 2987450 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2334. Min Act: -0.1700
Data Index: 1382339 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2334. Min Act: -0.1700
Data Index: 8311179 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2022. Min Act: -0.1693
Data Index: 587688 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2334. Min Act: -0.1700
Data Index: 2633288 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2022. Min Act: -0.1700
Data Index: 6222135 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.1709. Min Act: -0.1698
Data Index: 4706351 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2626412 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.1709. Min Act: -0.1700
Data Index: 1286624 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8897. Min Range: -6.8897
Max Act: 6.1397. Min Act: -0.1699
Data Index: 6770644 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19