Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3886. Min Range: -8.3886
Max Act: 8.3886. Min Act: -0.1700
Data Index: 3506621 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3886. Min Range: -8.3886
Max Act: 8.2636. Min Act: -0.1700
Data Index: 3549496 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3886. Min Range: -8.3886
Max Act: 8.2011. Min Act: -0.1700
Data Index: 729384 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3886. Min Range: -8.3886
Max Act: 8.1386. Min Act: -0.1700
Data Index: 2163602 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3886. Min Range: -8.3886
Max Act: 8.1386. Min Act: -0.1700
Data Index: 1554096 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.9511. Min Act: -0.1700
Data Index: 6298579 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.9511. Min Act: -0.1700
Data Index: 4520395 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.8886. Min Act: -0.1700
Data Index: 6549019 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7636. Min Act: -0.1700
Data Index: 7408877 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.8261. Min Act: -0.1700
Data Index: 1222340 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7636. Min Act: -0.1700
Data Index: 7533685 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.8261. Min Act: -0.1700
Data Index: 8014305 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7636. Min Act: -0.1700
Data Index: 5364864 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7011. Min Act: -0.1700
Data Index: 3330461 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7636. Min Act: -0.1700
Data Index: 2100085 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.6386. Min Act: -0.1700
Data Index: 600230 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7011. Min Act: -0.1700
Data Index: 3641528 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7011. Min Act: -0.1700
Data Index: 7569966 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7011. Min Act: -0.1700
Data Index: 7653867 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3886. Min Range: -8.3886
Max Act: 7.7636. Min Act: -0.1700
Data Index: 3903122 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19