Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.7690. Min Act: -0.1700
Data Index: 1306758 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6751. Min Act: -0.1700
Data Index: 753311 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6751. Min Act: -0.1700
Data Index: 6920632 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6751. Min Act: -0.1698
Data Index: 1226970 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6751. Min Act: -0.1700
Data Index: 2249929 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6751. Min Act: -0.1700
Data Index: 7373074 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6751. Min Act: -0.1700
Data Index: 753310 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6438. Min Act: -0.1700
Data Index: 4111110 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6438. Min Act: -0.1700
Data Index: 450182 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6438. Min Act: -0.1700
Data Index: 8173858 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6438. Min Act: -0.1700
Data Index: 812674 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1700
Data Index: 7123378 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6438. Min Act: -0.1700
Data Index: 989239 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1685
Data Index: 3045938 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1700
Data Index: 60579 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1700
Data Index: 420967 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1700
Data Index: 3375473 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1698
Data Index: 3449260 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1700
Data Index: 855797 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7690. Min Range: -3.7690
Max Act: 3.6125. Min Act: -0.1699
Data Index: 5306379 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19