Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3484. Min Range: -7.3484
Max Act: 7.3484. Min Act: -0.1700
Data Index: 4199690 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.9109. Min Act: -0.1700
Data Index: 1687875 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.8484. Min Act: -0.1700
Data Index: 3171934 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.6921. Min Act: -0.1700
Data Index: 2305064 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.6921. Min Act: -0.1700
Data Index: 5196032 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.6609. Min Act: -0.1700
Data Index: 3293218 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 2669128 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.6296. Min Act: -0.1700
Data Index: 1840322 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.6296. Min Act: -0.1700
Data Index: 4475067 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 7832717 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 1706278 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5359. Min Act: -0.1700
Data Index: 1391250 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5359. Min Act: -0.1700
Data Index: 5428628 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5359. Min Act: -0.1700
Data Index: 1035277 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 5371871 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5359. Min Act: -0.1700
Data Index: 1060782 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5046. Min Act: -0.1700
Data Index: 3158110 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5046. Min Act: -0.1700
Data Index: 444378 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.5046. Min Act: -0.1700
Data Index: 4095347 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3484. Min Range: -7.3484
Max Act: 6.4734. Min Act: -0.1700
Data Index: 2017532 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19