Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 950 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.5809. Min Act: -0.1700
Data Index: 1792434 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.4872. Min Act: -0.1700
Data Index: 5250051 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.4247. Min Act: -0.1700
Data Index: 1954914 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.4872. Min Act: -0.1700
Data Index: 5140396 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.4247. Min Act: -0.1700
Data Index: 4576318 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.4559. Min Act: -0.1700
Data Index: 3261204 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.4247. Min Act: -0.1700
Data Index: 3324952 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.4247. Min Act: -0.1700
Data Index: 7578559 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.3622. Min Act: -0.1700
Data Index: 5188984 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.3622. Min Act: -0.1700
Data Index: 7676593 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.2997. Min Act: -0.1700
Data Index: 825023 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.3622. Min Act: -0.1700
Data Index: 7474946 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.2997. Min Act: -0.1700
Data Index: 1442274 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.2997. Min Act: -0.1700
Data Index: 3467301 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.3309. Min Act: -0.1700
Data Index: 158077 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.2684. Min Act: -0.1700
Data Index: 2969247 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.2997. Min Act: -0.1700
Data Index: 2591578 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.2997. Min Act: -0.1700
Data Index: 4063833 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.3309. Min Act: -0.1700
Data Index: 2549926 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5809. Min Range: -6.5809
Max Act: 6.3622. Min Act: -0.1700
Data Index: 6050181 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19