Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2435. Min Range: -7.2435
Max Act: 7.2435. Min Act: -0.1700
Data Index: 150864 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.9935. Min Act: -0.1700
Data Index: 8790420 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.9622. Min Act: -0.1700
Data Index: 8534847 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.8685. Min Act: -0.1700
Data Index: 4845196 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.7747. Min Act: -0.1700
Data Index: 1528095 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.7747. Min Act: -0.1700
Data Index: 2339034 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.7435. Min Act: -0.1700
Data Index: 6158454 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.7435. Min Act: -0.1700
Data Index: 4663327 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.7435. Min Act: -0.1700
Data Index: 8168079 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.7122. Min Act: -0.1700
Data Index: 6291073 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.6810. Min Act: -0.1700
Data Index: 595158 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.6810. Min Act: -0.1700
Data Index: 2587180 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.6810. Min Act: -0.1700
Data Index: 3765789 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.6497. Min Act: -0.1700
Data Index: 5956219 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.6497. Min Act: -0.1700
Data Index: 2333163 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.6185. Min Act: -0.1700
Data Index: 2290113 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.6185. Min Act: -0.1700
Data Index: 3835092 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.5872. Min Act: -0.1700
Data Index: 4368401 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.5872. Min Act: -0.1700
Data Index: 2506309 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2435. Min Range: -7.2435
Max Act: 6.5560. Min Act: -0.1700
Data Index: 1601930 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19