Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.2591. Min Act: -0.1700
Data Index: 2721563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.2278. Min Act: -0.1700
Data Index: 5106962 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.1653. Min Act: -0.1700
Data Index: 90195 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.1341. Min Act: -0.1700
Data Index: 4168443 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.0716. Min Act: -0.1700
Data Index: 5678458 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.0403. Min Act: -0.1700
Data Index: 4168444 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.0403. Min Act: -0.1700
Data Index: 4009664 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.0403. Min Act: -0.1700
Data Index: 8521937 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.0403. Min Act: -0.1700
Data Index: 93316 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2591. Min Range: -5.2591
Max Act: 5.0403. Min Act: -0.1700
Data Index: 8078824 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9778. Min Act: -0.1700
Data Index: 3019174 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9466. Min Act: -0.1700
Data Index: 2249428 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9466. Min Act: -0.1700
Data Index: 472137 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9466. Min Act: -0.1700
Data Index: 6934719 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9466. Min Act: -0.1700
Data Index: 3790957 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9466. Min Act: -0.1700
Data Index: 1453269 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9466. Min Act: -0.1700
Data Index: 7153884 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9466. Min Act: -0.1700
Data Index: 1963931 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9153. Min Act: -0.1700
Data Index: 4093848 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2591. Min Range: -5.2591
Max Act: 4.9153. Min Act: -0.1700
Data Index: 4168163 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19