Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3924 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.8862. Min Act: -0.1700
Data Index: 8745103 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.7924. Min Act: -0.1700
Data Index: 4305676 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.4487. Min Act: -0.1700
Data Index: 6898218 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.4487. Min Act: -0.1700
Data Index: 1399382 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.4174. Min Act: -0.1700
Data Index: 3539366 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.3862. Min Act: -0.1700
Data Index: 994052 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.3549. Min Act: -0.1700
Data Index: 4126548 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.3237. Min Act: -0.1700
Data Index: 5581233 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.2924. Min Act: -0.1700
Data Index: 144294 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.2612. Min Act: -0.1700
Data Index: 971350 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.2612. Min Act: -0.1700
Data Index: 1814016 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.1987. Min Act: -0.1700
Data Index: 2337068 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6136954 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.1987. Min Act: -0.1700
Data Index: 4650861 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6370682 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.1987. Min Act: -0.1700
Data Index: 307410 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.1987. Min Act: -0.1700
Data Index: 7381299 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.1987. Min Act: -0.1699
Data Index: 6105607 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.1987. Min Act: -0.1700
Data Index: 323273 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8862. Min Range: -5.8862
Max Act: 5.1674. Min Act: -0.1700
Data Index: 2841762 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19