Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.4427. Min Act: -0.1700
Data Index: 8811421 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.3177. Min Act: -0.1700
Data Index: 7335310 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.1302. Min Act: -0.1700
Data Index: 5102307 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0677. Min Act: -0.1700
Data Index: 8283607 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0677. Min Act: -0.1700
Data Index: 6076864 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0677. Min Act: -0.1700
Data Index: 3448918 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0052. Min Act: -0.1700
Data Index: 4584608 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0052. Min Act: -0.1700
Data Index: 8630475 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.9427. Min Act: -0.1700
Data Index: 4197894 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0052. Min Act: -0.1700
Data Index: 4163414 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0052. Min Act: -0.1700
Data Index: 7791434 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0052. Min Act: -0.1700
Data Index: 815084 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4427. Min Range: -9.4427
Max Act: 9.0052. Min Act: -0.1700
Data Index: 2216352 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.8802. Min Act: -0.1700
Data Index: 1619311 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.8802. Min Act: -0.1700
Data Index: 2216355 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.9427. Min Act: -0.1700
Data Index: 231819 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.9427. Min Act: -0.1700
Data Index: 2856302 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.8802. Min Act: -0.1700
Data Index: 3625391 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.8802. Min Act: -0.1700
Data Index: 2797394 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4427. Min Range: -9.4427
Max Act: 8.8802. Min Act: -0.1700
Data Index: 4400809 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19