Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 220 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.3045. Min Act: -0.1700
Data Index: 2224931 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.2108. Min Act: -0.1700
Data Index: 1731848 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.2108. Min Act: -0.1700
Data Index: 7657928 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.1170. Min Act: -0.1700
Data Index: 4904978 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.0858. Min Act: -0.1700
Data Index: 2555228 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.0858. Min Act: -0.1700
Data Index: 5075566 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.0858. Min Act: -0.1700
Data Index: 2157294 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3045. Min Range: -5.3045
Max Act: 5.0233. Min Act: -0.1700
Data Index: 6785704 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.9920. Min Act: -0.1700
Data Index: 3811802 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.9608. Min Act: -0.1700
Data Index: 8163299 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.9920. Min Act: -0.1700
Data Index: 740073 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8983. Min Act: -0.1700
Data Index: 1534253 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8983. Min Act: -0.1700
Data Index: 6583355 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8670. Min Act: -0.1700
Data Index: 3927458 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8358. Min Act: -0.1700
Data Index: 871689 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8670. Min Act: -0.1700
Data Index: 736488 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8670. Min Act: -0.1700
Data Index: 6415836 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8358. Min Act: -0.1700
Data Index: 898553 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8045. Min Act: -0.1700
Data Index: 2555223 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3045. Min Range: -5.3045
Max Act: 4.8045. Min Act: -0.1700
Data Index: 761899 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19