Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3930 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.8732. Min Act: -0.1700
Data Index: 1216185 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.8732. Min Act: -0.1700
Data Index: 1216187 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.8107. Min Act: -0.1700
Data Index: 5345612 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7794. Min Act: -0.1700
Data Index: 7023147 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7794. Min Act: -0.1700
Data Index: 374173 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7169. Min Act: -0.1700
Data Index: 1926951 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7169. Min Act: -0.1700
Data Index: 4449653 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7169. Min Act: -0.1700
Data Index: 2236421 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7169. Min Act: -0.1700
Data Index: 6911375 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7169. Min Act: -0.1700
Data Index: 816570 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7169. Min Act: -0.1700
Data Index: 4701215 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6857. Min Act: -0.1700
Data Index: 2706582 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6857. Min Act: -0.1700
Data Index: 7591342 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6857. Min Act: -0.1700
Data Index: 3776780 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6857. Min Act: -0.1700
Data Index: 4162201 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6857. Min Act: -0.1700
Data Index: 1890565 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6544. Min Act: -0.1700
Data Index: 3401442 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6232. Min Act: -0.1700
Data Index: 1578755 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6544. Min Act: -0.1700
Data Index: 866940 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6232. Min Act: -0.1700
Data Index: 2706581 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19