Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1090 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.9335. Min Act: -0.1700
Data Index: 4197775 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.7147. Min Act: -0.1700
Data Index: 4065655 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.2460. Min Act: -0.1700
Data Index: 6573726 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.1835. Min Act: -0.1700
Data Index: 3111809 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.1522. Min Act: -0.1700
Data Index: 3578670 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0897. Min Act: -0.1700
Data Index: 2101091 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0897. Min Act: -0.1700
Data Index: 2904326 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0897. Min Act: -0.1700
Data Index: 3586618 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0585. Min Act: -0.1700
Data Index: 8125123 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0585. Min Act: -0.1700
Data Index: 467378 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0272. Min Act: -0.1700
Data Index: 5729122 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0272. Min Act: -0.1700
Data Index: 8790756 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0272. Min Act: -0.1700
Data Index: 6988313 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0272. Min Act: -0.1700
Data Index: 5501134 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0272. Min Act: -0.1700
Data Index: 6814900 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9335. Min Range: -6.9335
Max Act: 5.9960. Min Act: -0.1700
Data Index: 1003333 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9335. Min Range: -6.9335
Max Act: 5.9960. Min Act: -0.1700
Data Index: 4827064 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9335. Min Range: -6.9335
Max Act: 5.9960. Min Act: -0.1700
Data Index: 1221294 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9335. Min Range: -6.9335
Max Act: 6.0272. Min Act: -0.1700
Data Index: 4449638 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9335. Min Range: -6.9335
Max Act: 5.9960. Min Act: -0.1700
Data Index: 5322934 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19