Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.5623. Min Act: -0.1700
Data Index: 7352578 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.3748. Min Act: -0.1700
Data Index: 2211178 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.3123. Min Act: -0.1700
Data Index: 6569919 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.2810. Min Act: -0.1700
Data Index: 7185710 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.2810. Min Act: -0.1700
Data Index: 2282145 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.2498. Min Act: -0.1700
Data Index: 6505228 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.2498. Min Act: -0.1700
Data Index: 3624350 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.2185. Min Act: -0.1700
Data Index: 7060587 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1560. Min Act: -0.1700
Data Index: 2511706 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1873. Min Act: -0.1700
Data Index: 5736767 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1560. Min Act: -0.1700
Data Index: 1757325 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1248. Min Act: -0.1700
Data Index: 1886241 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1560. Min Act: -0.1700
Data Index: 129270 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1873. Min Act: -0.1700
Data Index: 4089897 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1560. Min Act: -0.1700
Data Index: 3803931 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1560. Min Act: -0.1700
Data Index: 918196 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1560. Min Act: -0.1700
Data Index: 2379087 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.0935. Min Act: -0.1700
Data Index: 5186109 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.0935. Min Act: -0.1700
Data Index: 6882680 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5623. Min Range: -5.5623
Max Act: 5.1248. Min Act: -0.1700
Data Index: 2871650 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19