Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1592 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2560. Min Range: -7.2560
Max Act: 7.2560. Min Act: -0.1700
Data Index: 7890985 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2560. Min Range: -7.2560
Max Act: 7.2248. Min Act: -0.1700
Data Index: 5133510 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2560. Min Range: -7.2560
Max Act: 7.2560. Min Act: -0.1700
Data Index: 6092719 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2560. Min Range: -7.2560
Max Act: 7.1935. Min Act: -0.1700
Data Index: 4383464 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2560. Min Range: -7.2560
Max Act: 7.1310. Min Act: -0.1700
Data Index: 5450813 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.9435. Min Act: -0.1700
Data Index: 4542544 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.9123. Min Act: -0.1700
Data Index: 2182781 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.8810. Min Act: -0.1700
Data Index: 1153965 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.8810. Min Act: -0.1700
Data Index: 7935866 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.8810. Min Act: -0.1700
Data Index: 8392150 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.8498. Min Act: -0.1700
Data Index: 4051364 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.8498. Min Act: -0.1700
Data Index: 2775235 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.7560. Min Act: -0.1700
Data Index: 8764348 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.7560. Min Act: -0.1700
Data Index: 1198172 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.7560. Min Act: -0.1700
Data Index: 2140318 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.7560. Min Act: -0.1700
Data Index: 3492650 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.7560. Min Act: -0.1700
Data Index: 4563414 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.6935. Min Act: -0.1700
Data Index: 5130843 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.6935. Min Act: -0.1700
Data Index: 5248107 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2560. Min Range: -7.2560
Max Act: 6.6935. Min Act: -0.1700
Data Index: 8385689 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19